© 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. 106170
    Prev
    Next
    INDEX
    Explanations

    descriptive language indicating abundance or richness

    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
    it
    -0.06
    out
    -0.06
    WWW
    -0.06
     nÃło
    -0.06
    wo
    -0.06
    gh
    -0.06
    and
    -0.06
    emoc
    -0.06
    irl
    -0.06
    wh
    -0.06
    POSITIVE LOGITS
    ÅĽcie
    0.08
    erdale
    0.07
     with
    0.07
    eteria
    0.07
    OLON
    0.07
    yš
    0.07
    ôn
    0.07
    omik
    0.07
    adoo
    0.07
    ernal
    0.07
    Activations Density 0.011%

    No Known Activations