© 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. 9-LLAMASCOPE-RES-131K
    6. 95486
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to data structures and online services

    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
    itized
    -0.07
    ocular
    -0.06
    oub
    -0.06
    loat
    -0.06
    INGLE
    -0.06
    ventus
    -0.06
    cedes
    -0.06
    essenger
    -0.06
    oints
    -0.06
    гл
    -0.06
    POSITIVE LOGITS
    verture
    0.07
    /off
    0.07
    chest
    0.07
    .rl
    0.06
     Feld
    0.06
    eken
    0.06
     Joel
    0.06
    thalm
    0.06
    egin
    0.06
    δή
    0.06
    Activations Density 0.265%

    No Known Activations