© 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. 4915
    Prev
    Next
    INDEX
    Explanations

    occupations and roles related to creative and professional identities

    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
    ohana
    -0.08
    åı«
    -0.08
     Called
    -0.08
    izon
    -0.08
    ÑĢоÑĩ
    -0.07
    InSection
    -0.07
    nid
    -0.07
    .metamodel
    -0.07
    ohan
    -0.07
    :NS
    -0.07
    POSITIVE LOGITS
    0.09
     of
    0.08
     from
    0.07
     extra
    0.06
     origin
    0.06
     arch
    0.06
     Royal
    0.06
     (
    0.06
    241
    0.06
     for
    0.06
    Activations Density 0.047%

    No Known Activations