© 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. 56141
    Prev
    Next
    INDEX
    Explanations

    repetitive phrases and statements that emphasize functions 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
    gage
    -0.07
    orgh
    -0.06
    arez
    -0.06
    rouch
    -0.06
    osit
    -0.06
    ander
    -0.06
    plor
    -0.06
    ress
    -0.06
    Paid
    -0.06
    ibble
    -0.06
    POSITIVE LOGITS
     indeed
    0.08
     Indeed
    0.07
    undle
    0.07
     Justice
    0.06
    SG
    0.06
    yles
    0.06
    raud
    0.06
    znam
    0.06
     Rae
    0.06
    Indeed
    0.06
    Activations Density 0.022%

    No Known Activations