© 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. 15-LLAMASCOPE-RES-131K
    11. 90233
    Prev
    Next
    INDEX
    Explanations

    comparisons regarding expectations or outcomes

    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
    /Dk
    -0.07
     coverage
    -0.06
    еÑģи
    -0.06
    ullan
    -0.06
    áf
    -0.06
    inspect
    -0.06
    ppelin
    -0.06
    uil
    -0.06
     erotik
    -0.06
    stup
    -0.06
    POSITIVE LOGITS
    hart
    0.07
    utherland
    0.06
     Capitals
    0.06
    ÑĢиÑĩ
    0.06
    ohn
    0.06
     Rounds
    0.06
    ius
    0.06
    egree
    0.06
    ipt
    0.06
    505
    0.05
    Activations Density 0.035%

    No Known Activations