© 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. 95378
    Prev
    Next
    INDEX
    Explanations

    past tense verbs associated with group dynamics or relationships

    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
    ees
    -0.08
    /Runtime
    -0.07
    çĭ
    -0.06
     vid
    -0.06
     sac
    -0.06
     probs
    -0.06
    å¥ij
    -0.06
    vit
    -0.06
    /process
    -0.06
    mrt
    -0.06
    POSITIVE LOGITS
     Wow
    0.07
    0.06
     ↵
    0.06
    Hmm
    0.06
     unpublished
    0.06
    iggins
    0.06
    .Requires
    0.06
    onth
    0.06
    rlen
    0.06
    _WARN
    0.06
    Activations Density 0.000%

    No Known Activations