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. 5479
    Prev
    Next
    INDEX
    Explanations

    phrases indicating conditional actions or recommendations

    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
    obel
    -0.07
    _DAT
    -0.07
    agg
    -0.07
    meli
    -0.07
    kur
    -0.07
    -tree
    -0.07
    ÑĢож
    -0.07
    åħ±åĴĮåĽ½
    -0.07
    zier
    -0.07
    immutable
    -0.07
    POSITIVE LOGITS
    inho
    0.06
    YY
    0.06
    #\
    0.06
    eh
    0.06
     fing
    0.06
    ptions
    0.05
     Bowman
    0.05
    orque
    0.05
    ç»ıèIJ¥
    0.05
     Nor
    0.05
    Activations Density 0.002%

    No Known Activations