© 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. 76379
    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
    iliz
    -0.07
    rego
    -0.07
    Äįen
    -0.06
    ombo
    -0.06
    onna
    -0.06
    aho
    -0.06
     IDb
    -0.06
     Bloody
    -0.06
     Leban
    -0.06
     impulse
    -0.06
    POSITIVE LOGITS
     Dove
    0.06
    Range
    0.06
    ìĥģëĭ´
    0.06
    _RD
    0.06
    Spin
    0.06
    snap
    0.06
    ãĥ³ãĥIJ
    0.06
    ãĤıãģļ
    0.06
     kad
    0.06
    ãĥ©ãĤ¯
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.