© 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. 118977
    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
    andan
    -0.06
    omore
    -0.06
    olut
    -0.06
    odie
    -0.06
    OUCH
    -0.06
     Eins
    -0.05
    ault
    -0.05
    imet
    -0.05
    :↵
    -0.05
    &r
    -0.05
    POSITIVE LOGITS
    ãĤ¹ãĥĨãĤ£
    0.09
    bidden
    0.07
    },'
    0.07
    Äįer
    0.07
    empre
    0.07
     didFinish
    0.07
    íĬ
    0.06
    -Za
    0.06
    èĢ
    0.06
    WRAPPER
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.