© 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. 83190
    Prev
    Next
    INDEX
    Explanations

    pronouns and phrases indicating personal involvement or the presence of individuals

    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
    å°½
    -0.07
     Garr
    -0.06
    òi
    -0.06
    aub
    -0.06
    ubar
    -0.06
    dy
    -0.06
    %p
    -0.06
    arkin
    -0.06
    вин
    -0.06
     dy
    -0.06
    POSITIVE LOGITS
     alist
    0.06
    iran
    0.06
    ziel
    0.06
     ÎľÎ¿Î½
    0.06
    eyer
    0.06
    Lookup
    0.06
    irit
    0.06
    esi
    0.06
    Clip
    0.06
    mÄĽ
    0.06
    Activations Density 0.044%

    No Known Activations