© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 84066
    Prev
    Next
    INDEX
    Explanations

    references to user interactions or feedback mechanisms

    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
     Sesso
    -0.07
    leur
    -0.07
    osos
    -0.07
    iloc
    -0.07
    ائÙĬØ©
    -0.07
    @brief
    -0.07
    ема
    -0.06
     indo
    -0.06
    deo
    -0.06
    juan
    -0.06
    POSITIVE LOGITS
    ged
    0.07
    Strict
    0.06
    anta
    0.06
    midd
    0.06
    usan
    0.06
    551
    0.06
    ilerek
    0.06
     Strict
    0.06
     à¤Ĩल
    0.06
    raph
    0.06
    Activations Density 0.001%

    No Known Activations