© 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. 75400
    Prev
    Next
    INDEX
    Explanations

    words that express degrees or quantities

    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
     resp
    -0.07
    berman
    -0.07
    оÑģÑĢед
    -0.07
    dict
    -0.06
    ãĥ¼ãĥĸ
    -0.06
    _malloc
    -0.06
    imson
    -0.06
    atitude
    -0.06
    cout
    -0.06
     Zub
    -0.06
    POSITIVE LOGITS
    ħn
    0.07
    NIL
    0.07
    ÂŁ
    0.07
    ãģĹãģı
    0.07
    hek
    0.06
    Schedulers
    0.06
    تز
    0.06
    aneously
    0.06
    .bunifuFlatButton
    0.06
    igh
    0.06
    Activations Density 0.026%

    No Known Activations