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. 5665
    Prev
    Next
    INDEX
    Explanations

    punctuation and phrases indicating relationships or comparisons

    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
    iland
    -0.07
    äm
    -0.07
    mal
    -0.06
    igli
    -0.06
    atta
    -0.06
    ussen
    -0.06
    rlen
    -0.06
    ricks
    -0.06
     her
    -0.06
    etc
    -0.06
    POSITIVE LOGITS
    onte
    0.07
     Burr
    0.07
    è²´
    0.07
    ,strong
    0.06
    ahoma
    0.06
    ãĥ³ãĥIJãĥ¼
    0.06
    .messaging
    0.06
    Disposed
    0.06
    rame
    0.06
     RESERVED
    0.06
    Activations Density 0.001%

    No Known Activations