© 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. 86114
    Prev
    Next
    INDEX
    Explanations

    references to personal and data privacy information

    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
    rone
    -0.07
    gap
    -0.07
    rike
    -0.07
    chers
    -0.07
    loor
    -0.07
    enheim
    -0.07
    inou
    -0.07
     strtol
    -0.07
    criptor
    -0.07
    geb
    -0.07
    POSITIVE LOGITS
     Dmit
    0.07
     Vance
    0.07
    yles
    0.06
     collected
    0.06
    ignet
    0.06
    AMI
    0.06
    aley
    0.06
    ault
    0.06
    apel
    0.06
     air
    0.05
    Activations Density 0.002%

    No Known Activations