© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4121
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Personal pronouns (including "she", "he", "they", "we", "us", "one", etc.) that reference individuals or entities within the text, often appearing in narrative contexts or when establishing perspective.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    laus
    -0.06
     mis
    -0.06
    sticky
    -0.06
    uhn
    -0.06
     Lucas
    -0.06
    ?p
    -0.06
    /or
    -0.05
     Helm
    -0.05
    points
    -0.05
     Lancaster
    -0.05
    POSITIVE LOGITS
     chatte
    0.07
    ibel
    0.07
    andom
    0.07
    ngr
    0.07
    antity
    0.07
    OnError
    0.07
    resse
    0.07
    ÑijÑĢ
    0.07
     escorte
    0.07
    amel
    0.06
    Activations Density 0.026%

    No Known Activations