© 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. 61245
    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
     Fon
    -0.06
    Disposition
    -0.06
     impr
    -0.06
     inde
    -0.05
    Ĩ
    -0.05
    اÙĨد
    -0.05
     imminent
    -0.05
     assort
    -0.05
     Gree
    -0.05
     Ready
    -0.05
    POSITIVE LOGITS
    uttle
    0.08
    ignon
    0.08
    hlen
    0.07
    umbs
    0.07
    olia
    0.07
    _mD
    0.07
    osto
    0.07
    aben
    0.07
    ticks
    0.07
    enguin
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.