© 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. 126321
    Prev
    Next
    INDEX
    Explanations

    instances of active voice and personal calls to action

    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
    ÑĢап
    -0.09
    ONTAL
    -0.07
    é¥
    -0.07
    olet
    -0.07
    oÅĽci
    -0.07
    AVOR
    -0.07
    .vendor
    -0.07
    Ìģ
    -0.07
    elps
    -0.07
     traveled
    -0.07
    POSITIVE LOGITS
    ver
    0.06
    holm
    0.06
     Mal
    0.06
     mal
    0.06
    man
    0.06
    kov
    0.06
     Sund
    0.06
    asz
    0.06
    ans
    0.05
    book
    0.05
    Activations Density 0.000%

    No Known Activations