© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 71589
    Prev
    Next
    INDEX
    Explanations

    actions involving giving or bestowing 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
    xn
    -0.07
    ync
    -0.07
    cid
    -0.07
    åĬŁ
    -0.07
     Triangle
    -0.06
     Thick
    -0.06
    iid
    -0.06
    icorn
    -0.06
    dep
    -0.06
     fortune
    -0.06
    POSITIVE LOGITS
    linkplain
    0.07
     Mour
    0.06
    ika
    0.06
     protected
    0.06
     Pr
    0.06
     Mug
    0.06
    smarty
    0.06
     satisfaction
    0.06
    ASIC
    0.06
    yleft
    0.06
    Activations Density 0.031%

    No Known Activations