© 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. 22-LLAMASCOPE-RES-131K
    11. 4090
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns and references to personal or collective identity

    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
     åħ¶
    -0.08
     technolog
    -0.07
    trys
    -0.07
    SError
    -0.07
     bekl
    -0.07
    kaz
    -0.06
    uyo
    -0.06
    å¨
    -0.06
    chw
    -0.06
    leep
    -0.06
    POSITIVE LOGITS
    elves
    0.07
    /her
    0.06
     «
    0.06
     own
    0.06
     peculiar
    0.06
    rael
    0.06
    æīĢ
    0.06
    ewith
    0.06
     pec
    0.06
    embros
    0.06
    Activations Density 0.117%

    No Known Activations