© 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. 78700
    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
     cess
    -0.07
     Harness
    -0.06
    356
    -0.06
     sanctioned
    -0.06
     possibilities
    -0.05
     jud
    -0.05
    Harness
    -0.05
     RC
    -0.05
    antry
    -0.05
    205
    -0.05
    POSITIVE LOGITS
     our
    0.08
    _DD
    0.07
    .appspot
    0.07
    akis
    0.07
    ãĥ¼ãĥŀ
    0.07
    Ñħодим
    0.07
    iversit
    0.07
    ekk
    0.07
    .dd
    0.07
    CPP
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.