© 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 EvalsExportsAPI 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. 60977
    Prev
    Next
    INDEX
    Explanations

    instances of directives or imperatives

    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
    QualifiedName
    -0.08
     Liberation
    -0.06
    hur
    -0.06
    olic
    -0.06
     Tiger
    -0.06
    782
    -0.06
    ungi
    -0.06
    endas
    -0.06
    REDENTIAL
    -0.05
    atis
    -0.05
    POSITIVE LOGITS
    /autoload
    0.07
    /backend
    0.07
    Ïģκ
    0.07
    _pet
    0.07
     shack
    0.06
     vej
    0.06
    .imag
    0.06
    edla
    0.06
    alic
    0.06
     smr
    0.06
    Activations Density 0.000%

    No Known Activations