© 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. 17-LLAMASCOPE-RES-131K
    11. 72493
    Prev
    Next
    INDEX
    Explanations

    strings of quotes and their surrounding context in code or text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ¦↵
    -0.06
    Âł
    -0.06
    uman
    -0.06
    âĢ¦
    -0.05
     "
    -0.05
     Pol
    -0.05
     âĢ¦
    -0.05
    ↵
    -0.05
     flam
    -0.05
    ,
    -0.05
    POSITIVE LOGITS
    .scalablytyped
    0.13
    léd
    0.09
    edImage
    0.09
    .updateDynamic
    0.08
    phis
    0.08
    $MESS
    0.08
    аниÑĨ
    0.08
     limburg
    0.08
    -FIRST
    0.08
    $LANG
    0.08
    Activations Density 0.015%

    No Known Activations