© 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. 654
    Prev
    Next
    INDEX
    Explanations

    programming configuration options and parameters

    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
    .Reporting
    -0.07
    asco
    -0.07
    azor
    -0.07
    agos
    -0.07
    äs
    -0.06
    μÏĢο
    -0.06
    ibri
    -0.06
    burgh
    -0.06
    oldem
    -0.06
    ISIBLE
    -0.06
    POSITIVE LOGITS
    EMS
    0.07
     Haram
    0.06
     Carpenter
    0.06
    bé
    0.06
    ihil
    0.06
    olson
    0.06
     standby
    0.06
    emale
    0.05
    yes
    0.05
     choice
    0.05
    Activations Density 0.000%

    No Known Activations