Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5170
    Prev
    Next
    INDEX
    Explanations

    themes related to gender roles and the perception of ambitious women

    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
    rana
    -0.07
    oble
    -0.07
    ulace
    -0.07
    MOTE
    -0.07
     âĹĦ
    -0.07
    onse
    -0.07
    anca
    -0.06
    ewis
    -0.06
    logg
    -0.06
    vor
    -0.06
    POSITIVE LOGITS
     hiring
    0.08
     Hiring
    0.08
    _office
    0.08
    .INSTANCE
    0.07
     Dil
    0.07
     cues
    0.07
     tokens
    0.07
     masculine
    0.06
     evaluations
    0.06
     warmth
    0.06
    Activations Density 0.007%

    No Known Activations