© 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. 60789
    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
    erville
    -0.07
    oran
    -0.07
    currentColor
    -0.06
    dust
    -0.06
    å®ĭä½ĵ
    -0.06
     "{$
    -0.06
    uth
    -0.06
     pÅĤ
    -0.06
    aren
    -0.06
     bitten
    -0.06
    POSITIVE LOGITS
    vertisement
    0.07
    ajar
    0.07
    iyat
    0.06
    iyor
    0.06
    ëĦ·
    0.06
    ieren
    0.06
    FU
    0.06
     cod
    0.06
    implicitly
    0.06
     laz
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.