© 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. 40689
    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
    ezier
    -0.08
     Peygamber
    -0.08
    RICS
    -0.07
    ssel
    -0.07
    aż
    -0.07
    illis
    -0.07
    ystore
    -0.07
    رÛĮاÙĨ
    -0.07
    'gc
    -0.07
    tml
    -0.07
    POSITIVE LOGITS
    icont
    0.06
     Singular
    0.06
    irk
    0.06
    uum
    0.06
    اÙģ
    0.06
    blank
    0.06
    and
    0.06
    -
    0.06
    ...
    0.06
    ÑĢеÑģ
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.