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. 84262
    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
       
    -0.07
     neighbourhood
    -0.06
     ìĹħëį°ìĿ´íĬ¸
    -0.06
    ombre
    -0.06
    uges
    -0.06
     trust
    -0.06
    utow
    -0.06
     yt
    -0.06
    ve
    -0.06
     
    -0.06
    POSITIVE LOGITS
    ourke
    0.08
    .Experimental
    0.07
    ffen
    0.07
    ANCELED
    0.07
    qv
    0.07
    strup
    0.07
    andas
    0.07
    afc
    0.07
     overhead
    0.07
     Clamp
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.