© 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. 61062
    Prev
    Next
    INDEX
    Explanations

    names of people associated with statements or actions

    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
    ucking
    -0.07
    /tiny
    -0.07
    èm
    -0.07
    ivic
    -0.07
    _procs
    -0.07
    .si
    -0.06
    brahim
    -0.06
    rale
    -0.06
     पड
    -0.06
    fluid
    -0.06
    POSITIVE LOGITS
     persön
    0.07
     company
    0.07
     personally
    0.06
     himself
    0.06
    company
    0.06
    .exec
    0.06
     tenure
    0.06
     baÅŁkan
    0.06
     оÑģобиÑģÑĤ
    0.06
    eus
    0.06
    Activations Density 0.041%

    No Known Activations