© 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. 61580
    Prev
    Next
    INDEX
    Explanations

    references to a female figure or entity, often indicated by the word "Her."

    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
    erc
    -0.07
    ra
    -0.07
    urn
    -0.07
    าà¸į
    -0.07
    s
    -0.06
    armed
    -0.06
    hrs
    -0.06
    aber
    -0.06
    abus
    -0.06
    è´§
    -0.06
    POSITIVE LOGITS
    bst
    0.10
    editary
    0.08
    itage
    0.08
     Majesty
    0.07
    ewith
    0.07
    OwnProperty
    0.07
    oku
    0.07
    hangi
    0.07
    encia
    0.07
    metic
    0.07
    Activations Density 0.015%

    No Known Activations