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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 27-LLAMASCOPE-RES-32K
    11. 18761
    Prev
    Next
    INDEX
    Explanations

    references to news sources and investigative content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .BLL
    -0.17
    swire
    -0.14
    аÑĢам
    -0.14
    _Panel
    -0.14
    åľ³
    -0.14
     XR
    -0.14
    OLUMNS
    -0.14
    ovatel
    -0.13
    enic
    -0.13
    czy
    -0.13
    POSITIVE LOGITS
     anchors
    0.30
     Ey
    0.29
     anchor
    0.28
     meteor
    0.26
    anchors
    0.26
    -anchor
    0.25
    Ey
    0.24
     Meteor
    0.24
     Anchor
    0.24
    anchor
    0.23
    Activations Density 0.060%

    No Known Activations