© 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. 126448
    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
    Ľ°
    -0.07
    urd
    -0.07
    trys
    -0.06
    alama
    -0.06
     Kam
    -0.06
     Shut
    -0.06
    ült
    -0.06
    å¡
    -0.06
     Peoples
    -0.06
     grit
    -0.05
    POSITIVE LOGITS
    andest
    0.08
    ardin
    0.08
     VÆ°á»Ŀn
    0.07
    ê¶ģ
    0.07
    oods
    0.07
     ÑĢаÐ
    0.07
    _digest
    0.06
    abor
    0.06
    odel
    0.06
    ogi
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.