© 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. 75040
    Prev
    Next
    INDEX
    Explanations

    references to cultural expressions and practices

    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
    ccione
    -0.07
    Ø°ÙĬ
    -0.07
     Laud
    -0.07
    kf
    -0.07
     Hate
    -0.07
    ocre
    -0.06
    roj
    -0.06
     Scient
    -0.06
    educ
    -0.06
    RefCount
    -0.06
    POSITIVE LOGITS
     anthropology
    0.09
    anth
    0.07
     anthrop
    0.07
     field
    0.07
    ̣
    0.07
     village
    0.07
     villagers
    0.07
     kin
    0.07
     Classic
    0.06
    field
    0.06
    Activations Density 0.064%

    No Known Activations