© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 31-LLAMASCOPE-RES-32K
    11. 5317
    Prev
    Next
    INDEX
    Explanations

    references to various forms of media, including podcasts, events, and community-focused content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _HERSHEY
    -0.14
     ServiceException
    -0.14
     cá»Ń
    -0.13
     بÙĨا
    -0.13
    inyin
    -0.12
    -Encoding
    -0.12
    Specifier
    -0.12
    -Identifier
    -0.12
    ollapsed
    -0.12
     PropertyValue
    -0.12
    POSITIVE LOGITS
     Productions
    0.28
    z
    0.25
     Minist
    0.24
     Collective
    0.23
     Studios
    0.23
     LLC
    0.22
     Records
    0.22
     Industries
    0.22
     collective
    0.21
     Podcast
    0.21
    Activations Density 0.294%

    No Known Activations