© 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. 16262
    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
    addock
    -0.08
    ейн
    -0.07
    ìĪł
    -0.06
    bai
    -0.05
    atz
    -0.05
    amy
    -0.05
     punct
    -0.05
     rod
    -0.05
    >
    -0.05
    elves
    -0.05
    POSITIVE LOGITS
     kulak
    0.08
    /ng
    0.07
    ilik
    0.07
    èĤ©
    0.07
    ilmek
    0.07
    inity
    0.07
    odont
    0.07
    kest
    0.07
    izon
    0.07
     shemale
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.