© 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. 118651
    Prev
    Next
    INDEX
    Explanations

    demographic data regarding sex

    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
    á»ĭch
    -0.08
    uiltin
    -0.07
    ullen
    -0.07
     Commercial
    -0.07
    akra
    -0.07
    uis
    -0.06
    arsi
    -0.06
    egin
    -0.06
    istinguished
    -0.06
    acia
    -0.06
    POSITIVE LOGITS
    |#
    0.07
    ÑĢаг
    0.07
    epar
    0.06
    Debugger
    0.06
    364
    0.06
    OLF
    0.06
    CLUD
    0.06
    /email
    0.06
    okol
    0.06
    rieved
    0.06
    Activations Density 0.000%

    No Known Activations