© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87667
    Prev
    Next
    INDEX
    Explanations

    numbers and figures presented in the 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
     con
    -0.07
     bunk
    -0.06
    addy
    -0.06
     inter
    -0.06
    æĿIJ
    -0.06
    alse
    -0.06
     interchange
    -0.06
     Vent
    -0.06
     Elem
    -0.06
     Stats
    -0.06
    POSITIVE LOGITS
     Score
    0.08
    oord
    0.07
    Score
    0.07
    score
    0.07
     score
    0.07
    $MESS
    0.07
    -score
    0.07
    twig
    0.07
    _score
    0.07
    anst
    0.07
    Activations Density 0.001%

    No Known Activations