© 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. 31081
    Prev
    Next
    INDEX
    Explanations

    references to authority figures or official roles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Subject references (pronouns, proper names, or role descriptions) that indicate who is performing actions or being described in narrative text.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    achel
    -0.09
    ilan
    -0.08
    моÑĢ
    -0.08
    аÑĢÑĩ
    -0.08
    Mocks
    -0.08
    CanBe
    -0.08
     teb
    -0.08
    ľ
    -0.08
    aland
    -0.08
    ónico
    -0.07
    POSITIVE LOGITS
     accordingly
    0.11
     reply
    0.10
     compliance
    0.10
     replies
    0.10
     complied
    0.09
     Reply
    0.09
     comply
    0.09
     replied
    0.09
     response
    0.08
    Reply
    0.08
    Activations Density 0.087%

    No Known Activations