© 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. 39158
    Prev
    Next
    INDEX
    Explanations

    mentions of specific constraints and events related to experimental or procedural data

    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
    aver
    -0.07
     sint
    -0.06
    RIES
    -0.06
    oyal
    -0.06
    _BS
    -0.06
     AÄŁ
    -0.06
    -fashion
    -0.05
    °ëĭ¤
    -0.05
    .aggregate
    -0.05
    quals
    -0.05
    POSITIVE LOGITS
    dit
    0.07
    们
    0.07
    ãĥ¬ãĤ¤
    0.07
     whose
    0.07
    ãĤ¤ãĤº
    0.06
     Rena
    0.06
    habit
    0.06
    ones
    0.06
     nữa
    0.06
    ynes
    0.06
    Activations Density 0.055%

    No Known Activations