© 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. 126200
    Prev
    Next
    INDEX
    Explanations

    terms related to data and data management

    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
     Robbins
    -0.07
     Dün
    -0.07
    afen
    -0.07
    uous
    -0.07
    aqu
    -0.07
    aque
    -0.07
    tuk
    -0.07
    еÑĤелÑĮ
    -0.07
    sWith
    -0.07
    .Butter
    -0.07
    POSITIVE LOGITS
    ils
    0.07
    hei
    0.07
    wy
    0.07
     Ves
    0.07
    aved
    0.06
    woke
    0.06
    we
    0.06
    w
    0.06
    :image
    0.06
    wit
    0.06
    Activations Density 0.007%

    No Known Activations