© 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. 62401
    Prev
    Next
    INDEX
    Explanations

    phrases related to requirements and guidelines

    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
    obili
    -0.06
    ghi
    -0.06
    onga
    -0.06
    atÃŃm
    -0.06
    illaume
    -0.06
    asaki
    -0.05
     everything
    -0.05
    ed
    -0.05
    ntp
    -0.05
    atem
    -0.05
    POSITIVE LOGITS
     particular
    0.14
     specific
    0.10
    chosen
    0.10
     chosen
    0.10
     конкÑĢеÑĤ
    0.10
    ichever
    0.09
    _specific
    0.09
    ftype
    0.08
     region
    0.08
    appropriate
    0.08
    Activations Density 0.038%

    No Known Activations