© 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. 17-LLAMASCOPE-RES-131K
    6. 57210
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    avig
    -0.08
    ench
    -0.07
    inkel
    -0.07
    ãĤ¤ãĥ¤
    -0.07
    onder
    -0.07
    ogan
    -0.07
    icha
    -0.07
    ÅĤaw
    -0.07
    енÑĭ
    -0.07
    avity
    -0.06
    POSITIVE LOGITS
    425
    0.07
    105
    0.07
    275
    0.07
    985
    0.06
    107
    0.06
    556
    0.06
     Activities
    0.06
    345
    0.06
    129
    0.06
    239
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.