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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 124010
    Prev
    Next
    INDEX
    Explanations

    concerns regarding safety, particularly for women in travel contexts

    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
    öl
    -0.07
     smugg
    -0.07
     Fut
    -0.06
    _GRE
    -0.06
     fabs
    -0.06
    à¸Ĭà¸Ļ
    -0.06
     Fab
    -0.06
    Äįer
    -0.06
     scor
    -0.06
    argins
    -0.06
    POSITIVE LOGITS
     safety
    0.18
     Safety
    0.17
    Safety
    0.16
    afety
    0.14
    å®īåħ¨
    0.14
     security
    0.14
     safer
    0.13
    security
    0.12
     unsafe
    0.12
     safe
    0.12
    Activations Density 0.113%

    No Known Activations