© 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. 86192
    Prev
    Next
    INDEX
    Explanations

    words or symbols indicating transitions or changes in context

    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
    ventus
    -0.08
    zin
    -0.08
    )|(
    -0.08
    Enlarge
    -0.07
    LLU
    -0.07
    ¯u
    -0.07
    abler
    -0.07
    ide
    -0.07
    imei
    -0.07
    igon
    -0.07
    POSITIVE LOGITS
    ra
    0.07
    ÑĮко
    0.07
     duo
    0.06
    uda
    0.06
     Pou
    0.06
    uard
    0.06
     QC
    0.06
     dyst
    0.06
     Fork
    0.05
    asa
    0.05
    Activations Density 0.000%

    No Known Activations