© 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. 76797
    Prev
    Next
    INDEX
    Explanations

    specifications and technical details related to hardware or electronics

    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
    .nb
    -0.07
    //{{
    -0.07
    é»
    -0.07
    elry
    -0.06
    oeff
    -0.06
    403
    -0.06
    577
    -0.06
    .scal
    -0.06
    ForResult
    -0.06
     Kaynak
    -0.06
    POSITIVE LOGITS
    inn
    0.06
    rett
    0.06
    ledge
    0.06
    ennen
    0.06
     Linden
    0.06
    anst
    0.06
     Guerrero
    0.06
    osate
    0.06
    onium
    0.06
    isode
    0.06
    Activations Density 0.001%

    No Known Activations