© 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. 75318
    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
    _INITIALIZER
    -0.07
    ë§ŀ
    -0.06
     Hire
    -0.06
    stakes
    -0.06
    üss
    -0.06
     Sadd
    -0.06
    .shader
    -0.06
    enda
    -0.06
    Hugh
    -0.06
    lington
    -0.06
    POSITIVE LOGITS
    tre
    0.07
    ent
    0.06
    uyu
    0.06
    tar
    0.06
    Ñıб
    0.06
    izza
    0.06
     dialect
    0.06
    verity
    0.05
    tru
    0.05
    reme
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.