Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 77220
    Prev
    Next
    INDEX
    Explanations

    references to assistance programs and their related requirements

    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
    erdale
    -0.07
    .realm
    -0.07
    ailability
    -0.06
    olon
    -0.06
    /../
    -0.06
    ASCADE
    -0.06
    531
    -0.06
    plevel
    -0.06
    asks
    -0.06
    269
    -0.06
    POSITIVE LOGITS
    Ñİ
    0.07
    idar
    0.06
     cash
    0.06
    acz
    0.06
     Hod
    0.06
     independence
    0.06
    autoload
    0.06
    usc
    0.06
    subs
    0.06
    att
    0.06
    Activations Density 0.000%

    No Known Activations