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. 56148
    Prev
    Next
    INDEX
    Explanations

    warnings or cautionary advice regarding plot details or spoilers

    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
    кÑģ
    -0.06
    _Api
    -0.06
     воÑĤ
    -0.06
    utherland
    -0.06
    amo
    -0.06
    áºŃy
    -0.06
     undermin
    -0.06
    ",[
    -0.06
    Ñıн
    -0.06
    åľ¨çº¿è§Ĥçľĭ
    -0.06
    POSITIVE LOGITS
    udic
    0.06
    chein
    0.06
    inea
    0.06
    OUNT
    0.06
    itzer
    0.06
    iko
    0.06
    OffsetTable
    0.06
    ToPoint
    0.06
    illery
    0.06
     recent
    0.06
    Activations Density 0.002%

    No Known Activations