© 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. 16496
    Prev
    Next
    INDEX
    Explanations

    requests for actions or inquiries directed towards others

    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
    ighth
    -0.08
    zung
    -0.07
    osas
    -0.07
    pillar
    -0.07
    enas
    -0.07
    Editable
    -0.07
    370
    -0.06
    geh
    -0.06
    plies
    -0.06
    omor
    -0.06
    POSITIVE LOGITS
     consideration
    0.11
     acceptance
    0.09
     forgiveness
    0.09
     readers
    0.08
     attention
    0.08
     consider
    0.08
     allowance
    0.08
     reader
    0.08
    attention
    0.08
     Consider
    0.08
    Activations Density 0.039%

    No Known Activations