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. 5626
    Prev
    Next
    INDEX
    Explanations

    the letter 'S' in different contexts, likely indicating a focus on specific names or titles

    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
    iasi
    -0.08
    inces
    -0.07
    upp
    -0.07
    ites
    -0.07
    GENCY
    -0.07
    óng
    -0.06
    bsolute
    -0.06
    pora
    -0.06
     Mast
    -0.06
    us
    -0.06
    POSITIVE LOGITS
    izr
    0.07
    hx
    0.07
     dep
    0.06
    velt
    0.06
     subt
    0.06
     pard
    0.06
    ABC
    0.06
    lient
    0.06
    .EX
    0.06
    гал
    0.06
    Activations Density 0.019%

    No Known Activations