© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 54673
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate the provision of assistance or supportive information

    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
    _TB
    -0.07
    edList
    -0.07
    heim
    -0.07
    stagram
    -0.07
    anian
    -0.07
    ed
    -0.07
    ocator
    -0.07
    -0.06
    idlo
    -0.06
    mpz
    -0.06
    POSITIVE LOGITS
    ness
    0.13
    NESS
    0.09
    lest
    0.08
    ly
    0.08
    Ùĩ
    0.07
    s
    0.07
    /use
    0.07
    shire
    0.07
    ship
    0.06
    atcher
    0.06
    Activations Density 0.007%

    No Known Activations