Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5321
    Prev
    Next
    INDEX
    Explanations

    greetings and friendly salutations

    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
    ov
    -0.07
    ipp
    -0.07
    à¸ķà¸Ļ
    -0.07
    asu
    -0.06
    ceed
    -0.06
    ------+------+
    -0.06
    IONS
    -0.06
    utf
    -0.06
    ienia
    -0.06
    ire
    -0.06
    POSITIVE LOGITS
     everyone
    0.10
    ,↵↵
    0.09
     everybody
    0.08
     *,↵
    0.08
     again
    0.08
    ,č↵
    0.08
     there
    0.08
     guys
    0.08
     Everyone
    0.08
    ,↵
    0.07
    Activations Density 0.004%

    No Known Activations