© 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. 16716
    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
     hete
    -0.07
    swer
    -0.07
    izik
    -0.07
    iminal
    -0.07
    oram
    -0.07
    atural
    -0.06
    isko
    -0.06
    _DRIVE
    -0.06
    orthy
    -0.06
    imento
    -0.06
    POSITIVE LOGITS
     éĹ
    0.07
    .ny
    0.06
    814
    0.06
     overriding
    0.06
    borough
    0.06
    istring
    0.05
     rowspan
    0.05
    bond
    0.05
     cond
    0.05
    SGlobal
    0.05
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.