© 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. 84282
    Prev
    Next
    INDEX
    Explanations

    references to the name "Peter."

    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
     addCriterion
    -0.08
    /stdc
    -0.08
    enario
    -0.08
    arna
    -0.08
    ewolf
    -0.08
    uetype
    -0.08
    /WebAPI
    -0.07
    ved
    -0.07
    ihan
    -0.07
    alo
    -0.07
    POSITIVE LOGITS
    borough
    0.09
    house
    0.07
    ah
    0.07
     Damian
    0.07
     thumb
    0.06
    thumb
    0.06
    head
    0.06
    hof
    0.06
    169
    0.06
     Giang
    0.06
    Activations Density 0.008%

    No Known Activations