© 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. 104527
    Prev
    Next
    INDEX
    Explanations

    phrases that express suggestions or alternatives

    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
    alon
    -0.08
    anford
    -0.07
    liž
    -0.07
    nonnull
    -0.07
    òng
    -0.07
    yles
    -0.07
    ÑĢаÑģ
    -0.06
    _compat
    -0.06
    &type
    -0.06
    comed
    -0.06
    POSITIVE LOGITS
     simply
    0.23
     Simply
    0.18
     simplement
    0.17
    Simply
    0.16
     пÑĢоÑģÑĤо
    0.16
     just
    0.15
     einfach
    0.13
     ê·¸ëĥ¥
    0.13
    just
    0.12
    缴æİ¥
    0.12
    Activations Density 0.062%

    No Known Activations