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. 43967
    Prev
    Next
    INDEX
    Explanations

    specific names and references to popular culture and significant events

    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
    OLA
    -0.08
    UDA
    -0.08
    BY
    -0.08
    ENER
    -0.07
    ERA
    -0.07
    .SP
    -0.07
    \:
    -0.07
     ::
    -0.07
    HT
    -0.07
    @student
    -0.07
    POSITIVE LOGITS
    ÂŃ
    0.11
     ÂŃ
    0.08
    ¬
    0.08
    ÂŃn
    0.08
    ÂŃs
    0.07
    aland
    0.07
    -esque
    0.07
     freaking
    0.07
    -↵
    0.07
     Alley
    0.07
    Activations Density 0.037%

    No Known Activations