© 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. 78436
    Prev
    Next
    INDEX
    Explanations

    phrases and punctuation typically associated with web links or citations

    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
     serialVersionUID
    -0.06
    nun
    -0.06
    626
    -0.06
    /tty
    -0.05
    regs
    -0.05
    rega
    -0.05
    èĦ
    -0.05
    RequestId
    -0.05
     regards
    -0.05
     unsupported
    -0.05
    POSITIVE LOGITS
    klä
    0.07
    kv
    0.07
    ecial
    0.07
    osu
    0.06
    erral
    0.06
    cli
    0.06
    ichen
    0.06
    cheon
    0.06
    akt
    0.06
    Ø·
    0.06
    Activations Density 0.003%

    No Known Activations