© 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. 31-LLAMASCOPE-RES-32K
    11. 7394
    Prev
    Next
    INDEX
    Explanations

    prominent names and individuals historically relevant to various topics

    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
    459
    -0.15
    riz
    -0.14
    edar
    -0.14
    ryn
    -0.14
    (Xml
    -0.14
    @Xml
    -0.14
     Jord
    -0.14
     Kanun
    -0.13
    ÑĢин
    -0.13
     Rash
    -0.13
    POSITIVE LOGITS
     Robert
    1.23
    Robert
    1.12
     robert
    1.03
     Bob
    0.93
     Roberts
    0.85
     ÐłÐ¾Ð±
    0.85
     Robertson
    0.84
    Bob
    0.82
     bob
    0.80
    bob
    0.69
    Activations Density 0.030%

    No Known Activations