Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5587
    Prev
    Next
    INDEX
    Explanations

    terms associated with baseball plays and actions

    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
    ÑŁ
    -0.08
    APH
    -0.08
    rts
    -0.07
    oog
    -0.07
    zim
    -0.07
    ullo
    -0.07
    _resolver
    -0.07
     奥
    -0.07
    affen
    -0.07
    ropp
    -0.07
    POSITIVE LOGITS
     plateau
    0.06
     ret
    0.06
    anking
    0.06
    ensa
    0.06
    td
    0.05
     banking
    0.05
     banc
    0.05
     bore
    0.05
     Plate
    0.05
     respective
    0.05
    Activations Density 0.000%

    No Known Activations