© 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. 15-LLAMASCOPE-RES-131K
    6. 104108
    Prev
    Next
    INDEX
    Explanations

    references to vague or unspecified concepts and ideas

    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
    eden
    -0.06
    tery
    -0.06
     Pose
    -0.06
    elda
    -0.06
    enties
    -0.06
     Marsh
    -0.06
     Asked
    -0.06
    Marsh
    -0.06
    immer
    -0.05
    _exempt
    -0.05
    POSITIVE LOGITS
    rega
    0.08
     borderTop
    0.07
    ewire
    0.07
    ýš
    0.07
     like
    0.07
     như
    0.07
    bern
    0.07
    ToSelector
    0.07
     воÑĤ
    0.07
     likes
    0.07
    Activations Density 0.007%

    No Known Activations