© 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. 69987
    Prev
    Next
    INDEX
    Explanations

    expressions of personal opinions and evaluations

    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
    annis
    -0.07
    Äįet
    -0.06
    contr
    -0.06
    icus
    -0.06
    eldon
    -0.06
     mess
    -0.06
    orgh
    -0.06
    анÑģ
    -0.06
    antha
    -0.05
    poss
    -0.05
    POSITIVE LOGITS
     CONTEXT
    0.09
    abee
    0.09
    éľŀ
    0.08
    ãģĹãĤĩãģĨ
    0.08
    æ¯ķ
    0.08
     Explanation
    0.07
     excuses
    0.07
    CONTEXT
    0.07
     Context
    0.07
     context
    0.07
    Activations Density 0.044%

    No Known Activations