© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 87937
    Prev
    Next
    INDEX
    Explanations

    actions involving pointing or indicating towards something

    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
     gridColumn
    -0.08
    amma
    -0.08
    gré
    -0.07
    ottes
    -0.07
    784
    -0.07
    ÏĩÏİ
    -0.06
    _DEPRECATED
    -0.06
    ycop
    -0.06
    jk
    -0.06
    inka
    -0.06
    POSITIVE LOGITS
    IES
    0.07
     Gest
    0.06
     gest
    0.06
    ches
    0.06
    ies
    0.06
     Flame
    0.06
    lein
    0.06
    Clazz
    0.06
     man
    0.06
     heaven
    0.06
    Activations Density 0.010%

    No Known Activations