© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74740
    Prev
    Next
    INDEX
    Explanations

    references to news articles and press releases

    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
     Socorro
    -0.07
    ะ
    -0.06
    andal
    -0.06
    309
    -0.06
    esiz
    -0.06
     Weiner
    -0.06
     policemen
    -0.06
    eling
    -0.06
     زÙħ
    -0.06
     subst
    -0.06
    POSITIVE LOGITS
     press
    0.13
     announcement
    0.09
     Press
    0.09
    Press
    0.08
     PRESS
    0.08
    press
    0.08
     release
    0.08
     company
    0.08
     statement
    0.07
     Announcement
    0.07
    Activations Density 0.030%

    No Known Activations