© 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. 116932
    Prev
    Next
    INDEX
    Explanations

    questions about quantity and identity

    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
    uml
    -0.08
    egin
    -0.06
     should
    -0.06
    leich
    -0.06
     probably
    -0.06
     reasons
    -0.06
    rait
    -0.06
    isper
    -0.06
     Beginning
    -0.06
    ifact
    -0.06
    POSITIVE LOGITS
    ëĬIJ
    0.10
    ä½ł
    0.07
    ddit
    0.07
    ãĥĭãĤ¢
    0.07
    799
    0.07
     youre
    0.07
    /how
    0.06
     chosen
    0.06
    _SAMPLES
    0.06
    ÙĨس
    0.06
    Activations Density 0.020%

    No Known Activations