© 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. 775
    Prev
    Next
    INDEX
    Explanations

    phrases related to ideas and exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ibold
    -0.07
    aison
    -0.06
    ácil
    -0.06
    uitar
    -0.06
    izoph
    -0.06
    urve
    -0.06
    pute
    -0.06
    udem
    -0.06
    readcr
    -0.06
    icap
    -0.06
    POSITIVE LOGITS
     executions
    0.07
    ots
    0.06
    ODO
    0.06
    .ActionListener
    0.06
    IFS
    0.06
    ynes
    0.06
    985
    0.06
     Boo
    0.06
    ãģ¤ãģ¶
    0.06
    leigh
    0.06
    Activations Density 0.007%

    No Known Activations