© 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. 62739
    Prev
    Next
    INDEX
    Explanations

    themes related to identity and self-perception

    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
    itra
    -0.06
    pedo
    -0.06
    ixin
    -0.06
    ng
    -0.06
     retro
    -0.06
     fixation
    -0.06
    IPA
    -0.06
    lap
    -0.06
     blind
    -0.06
    getOption
    -0.06
    POSITIVE LOGITS
     persona
    0.09
     mask
    0.08
     masks
    0.08
     Persona
    0.08
    persona
    0.07
    eÄį
    0.07
     roles
    0.07
    mask
    0.07
     Masks
    0.07
     OUTER
    0.07
    Activations Density 0.026%

    No Known Activations