© 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. 118064
    Prev
    Next
    INDEX
    Explanations

    references to young female performers or artists

    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
     Adult
    -0.10
     adult
    -0.09
     grads
    -0.08
     adulte
    -0.08
    graduate
    -0.08
    Adult
    -0.07
     graduate
    -0.07
    adult
    -0.07
     adultes
    -0.07
     Brewery
    -0.07
    POSITIVE LOGITS
     Junior
    0.07
     school
    0.07
     boys
    0.07
     pint
    0.06
    963
    0.06
     junior
    0.06
     prec
    0.06
     girls
    0.06
    orz
    0.06
    chen
    0.06
    Activations Density 0.055%

    No Known Activations