© 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. 119141
    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
    .locals
    -0.07
    485
    -0.06
    agine
    -0.06
     ç¨
    -0.06
    622
    -0.06
    ç¨
    -0.05
    رÙģ
    -0.05
    åľ°è¯´
    -0.05
    zion
    -0.05
    opoulos
    -0.05
    POSITIVE LOGITS
    inet
    0.08
    .scalablytyped
    0.06
    ynamics
    0.06
    erner
    0.06
    itler
    0.06
    erts
    0.06
    ught
    0.06
     kron
    0.06
    -
    0.06
    ucchini
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.