© 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. 108090
    Prev
    Next
    INDEX
    Explanations

    actions and interactions involving physical objects

    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
    ngle
    -0.07
    icari
    -0.07
    ebi
    -0.07
     erotik
    -0.06
    iene
    -0.06
     Trend
    -0.06
    StackNavigator
    -0.06
    _MAPPING
    -0.06
     trend
    -0.06
     Tide
    -0.06
    POSITIVE LOGITS
    ignum
    0.07
    ingo
    0.07
    oltage
    0.06
    .NewReader
    0.06
    наÑĩала
    0.06
    XHR
    0.06
    ondon
    0.06
     ceremon
    0.06
    FirstResponder
    0.06
    armac
    0.06
    Activations Density 0.020%

    No Known Activations