© 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. 77014
    Prev
    Next
    INDEX
    Explanations

    instances of kindness or generous behaviors

    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
    ppe
    -0.07
    ernel
    -0.06
    UCH
    -0.06
    å§ī
    -0.06
    iece
    -0.06
    à¸ĸ
    -0.06
     ØŃد
    -0.06
    pty
    -0.06
     ern
    -0.06
     Blonde
    -0.06
    POSITIVE LOGITS
    cul
    0.07
    antly
    0.06
     taking
    0.06
     considering
    0.06
     let
    0.06
    ixa
    0.06
     provid
    0.06
    edException
    0.06
    offsetof
    0.06
    descending
    0.06
    Activations Density 0.006%

    No Known Activations