© 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. 79810
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly notable figures and recurring names in a text

    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
    er
    -0.07
    acas
    -0.07
    rada
    -0.06
    yleft
    -0.06
    yt
    -0.06
    _diag
    -0.06
    alet
    -0.06
    pis
    -0.06
    lio
    -0.06
    ặn
    -0.06
    POSITIVE LOGITS
    ellaneous
    0.07
    embro
    0.07
    ockey
    0.07
    oman
    0.07
    arp
    0.07
    icious
    0.07
    embros
    0.07
    anker
    0.07
    RIX
    0.07
    ound
    0.07
    Activations Density 0.002%

    No Known Activations