© 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. 71386
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating ownership or belonging

    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
    SCII
    -0.07
    ried
    -0.07
    /stdc
    -0.07
    kili
    -0.07
     kayn
    -0.07
    .WinForms
    -0.07
    itur
    -0.07
    icode
    -0.07
    isté
    -0.07
    illion
    -0.07
    POSITIVE LOGITS
    ķ
    0.07
     Archer
    0.06
     spare
    0.06
    026
    0.06
     entire
    0.06
    977
    0.06
     Challenger
    0.06
     Geld
    0.06
     probation
    0.06
     precious
    0.05
    Activations Density 0.007%

    No Known Activations