© 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. 70936
    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
    ,
    -0.06
    625
    -0.06
    µ
    -0.06
    éłĺ
    -0.06
    280
    -0.06
    981
    -0.06
    agas
    -0.05
     revert
    -0.05
    él
    -0.05
    982
    -0.05
    POSITIVE LOGITS
    ãĥ©ãĤ¹
    0.08
    /stdc
    0.08
     onBind
    0.08
    andr
    0.07
    Isl
    0.07
     doma
    0.07
    mojom
    0.07
     Ñģоп
    0.07
    jedn
    0.07
    -Identifier
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.