© 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. 106192
    Prev
    Next
    INDEX
    Explanations

    calls to action or invitations to participate in some activity

    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
    569
    -0.07
    ersh
    -0.07
    amedi
    -0.06
    iring
    -0.06
     Alone
    -0.06
     Enemies
    -0.06
    298
    -0.06
    -0.06
    oce
    -0.06
     alone
    -0.06
    POSITIVE LOGITS
     attention
    0.08
    IPS
    0.08
    -action
    0.08
     action
    0.07
    UNUSED
    0.07
    orney
    0.07
     arms
    0.07
    _codec
    0.07
     Duty
    0.07
    icode
    0.07
    Activations Density 0.011%

    No Known Activations