© 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. 120117
    Prev
    Next
    INDEX
    Explanations

    emotional expressions related to joy and vulnerability

    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
    iw
    -0.07
    umbs
    -0.07
     Cli
    -0.06
    ÑĥеÑĤ
    -0.06
    549
    -0.06
    NotAllowed
    -0.06
     Leo
    -0.06
    _slices
    -0.06
    .dds
    -0.06
    vl
    -0.06
    POSITIVE LOGITS
     explode
    0.07
     Suff
    0.07
    uze
    0.07
    çĪĨ
    0.07
     explodes
    0.07
     suff
    0.06
     implode
    0.06
     bursting
    0.06
     Burst
    0.06
    akov
    0.06
    Activations Density 0.042%

    No Known Activations