© 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. 129201
    Prev
    Next
    INDEX
    Explanations

    inquiries related to concepts, actions, or states of being

    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
    lse
    -0.07
    lining
    -0.06
    emens
    -0.06
    uxe
    -0.06
    ansen
    -0.06
    vise
    -0.06
    žený
    -0.06
    uros
    -0.06
    erman
    -0.06
    resse
    -0.06
    POSITIVE LOGITS
    iny
    0.07
    haar
    0.07
    owitz
    0.06
    esson
    0.06
    esium
    0.06
     seem
    0.06
    zo
    0.06
    tg
    0.06
     respectively
    0.06
    _SUPPORT
    0.06
    Activations Density 0.026%

    No Known Activations