© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82691
    Prev
    Next
    INDEX
    Explanations

    instances of calls to action or prompts for further reading

    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
    itez
    -0.07
    cÃŃ
    -0.07
    undo
    -0.06
    odyn
    -0.06
    _lite
    -0.06
    _ATOMIC
    -0.06
    FileVersion
    -0.06
    ÑģÑĤÑĢи
    -0.06
     kuv
    -0.06
     voks
    -0.06
    POSITIVE LOGITS
    agoon
    0.08
    owell
    0.07
    .scalablytyped
    0.07
    alls
    0.07
    ziej
    0.06
    iot
    0.06
    amacare
    0.06
    inem
    0.06
    ĶåĽŀ
    0.06
    .PropTypes
    0.06
    Activations Density 0.002%

    No Known Activations