© 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. 77022
    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
    otas
    -0.06
    monic
    -0.06
    edy
    -0.06
    iland
    -0.06
    ata
    -0.06
    äh
    -0.06
    isl
    -0.05
    ANNEL
    -0.05
    /groups
    -0.05
    atti
    -0.05
    POSITIVE LOGITS
    áv
    0.07
    éijij
    0.07
    abei
    0.07
    QUIRES
    0.07
    vem
    0.07
    Trap
    0.07
    $MESS
    0.07
     kvin
    0.07
    PEC
    0.07
    cem
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.