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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96139
    Prev
    Next
    INDEX
    Explanations

    action verbs related to decision-making and participation

    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
    /from
    -0.11
    /by
    -0.09
    /of
    -0.08
    aped
    -0.07
    /or
    -0.07
    bject
    -0.07
    езд
    -0.07
    reds
    -0.07
    aron
    -0.07
    /on
    -0.07
    POSITIVE LOGITS
    isch
    0.06
     ÑŁ
    0.06
    اÙĨ
    0.06
    ÏĦαι
    0.06
    ovÃŃ
    0.06
     Dio
    0.06
    /***/
    0.06
    Ä±ÅŁÄ±k
    0.06
    ëĭ¥
    0.06
    .heading
    0.06
    Activations Density 0.217%

    No Known Activations