© 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. 119122
    Prev
    Next
    INDEX
    Explanations

    references to notable individuals and their contributions

    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
    azo
    -0.07
     crystal
    -0.07
    dna
    -0.06
    DNA
    -0.06
    DCF
    -0.06
     minimum
    -0.06
     Secret
    -0.06
     Stress
    -0.06
    ayet
    -0.06
     Debate
    -0.06
    POSITIVE LOGITS
    _lite
    0.07
    isay
    0.07
    ÐIJÑĢÑħÑĸв
    0.07
    .rawValue
    0.07
    iyim
    0.07
    bra
    0.07
     brain
    0.07
    .jobs
    0.07
    STM
    0.07
     Patients
    0.07
    Activations Density 0.001%

    No Known Activations