© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 129713
    Prev
    Next
    INDEX
    Explanations

    titles and roles associated with artistic and creative professions

    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
     zas
    -0.08
    ewise
    -0.07
    hausen
    -0.07
    okud
    -0.07
    erea
    -0.07
    _Lean
    -0.07
    _Tis
    -0.07
    asurer
    -0.07
    rowsable
    -0.06
    ertype
    -0.06
    POSITIVE LOGITS
     extra
    0.07
    otle
    0.07
    @s
    0.06
     who
    0.06
    @m
    0.06
     giant
    0.06
    ucch
    0.06
     ga
    0.05
     Nic
    0.05
    whose
    0.05
    Activations Density 0.037%

    No Known Activations