© 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. 39136
    Prev
    Next
    INDEX
    Explanations

    conditional phrases involving actions and consequences

    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
    á»ĩ
    -0.07
    ivel
    -0.07
    iveau
    -0.07
    ambi
    -0.06
    /cop
    -0.06
    urn
    -0.06
    OLER
    -0.06
    EI
    -0.06
    sei
    -0.06
    USR
    -0.06
    POSITIVE LOGITS
    ought
    0.07
     Arabian
    0.07
    _pedido
    0.06
     Correction
    0.06
    .habbo
    0.06
     Tas
    0.06
    aster
    0.05
    _published
    0.05
     Cain
    0.05
    _registro
    0.05
    Activations Density 0.000%

    No Known Activations