© 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. 15-LLAMASCOPE-RES-131K
    11. 26885
    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
    arkin
    -0.08
    ayah
    -0.07
    hiba
    -0.07
     sqr
    -0.07
    perate
    -0.06
    earer
    -0.06
    olon
    -0.06
    rien
    -0.06
    erez
    -0.06
    adia
    -0.06
    POSITIVE LOGITS
     Grat
    0.07
    eper
    0.07
    usted
    0.07
     Gur
    0.07
    -addon
    0.06
    boss
    0.06
    asing
    0.06
    emailer
    0.06
    loyment
    0.06
    .semantic
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.