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. 31-LLAMASCOPE-RES-131K
    6. 43844
    Prev
    Next
    INDEX
    Explanations

    locations and their associated numerical identifiers or addresses

    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
    -One
    -0.06
    (éĩij
    -0.06
    ï¼ĭ
    -0.06
    ð
    -0.06
    noinspection
    -0.06
    .override
    -0.06
    Ä©
    -0.06
    _DISCONNECT
    -0.06
    GRAM
    -0.06
    "."
    -0.06
    POSITIVE LOGITS
     USA
    0.09
     PhD
    0.08
     OK
    0.08
     ,
    0.08
     MainAxisAlignment
    0.07
     Animalia
    0.07
     IL
    0.07
     FontWeight
    0.07
     England
    0.07
    ,
    0.07
    Activations Density 0.010%

    No Known Activations