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. 43558
    Prev
    Next
    INDEX
    Explanations

    specific instances of character names or identifiers in a text

    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
     c
    -0.07
    YN
    -0.07
     Derrick
    -0.06
     Davis
    -0.06
    imus
    -0.06
    ncia
    -0.06
    ienes
    -0.06
    ・・
    -0.06
    ETS
    -0.06
    jen
    -0.06
    POSITIVE LOGITS
    er
    0.11
    aran
    0.09
    Ķ
    0.08
    iran
    0.08
    zego
    0.07
    AndView
    0.07
    arding
    0.07
    Queryable
    0.07
    ató
    0.07
    arah
    0.07
    Activations Density 0.003%

    No Known Activations