© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16748
    Prev
    Next
    INDEX
    Explanations

    references to observational and clinical studies, particularly those involving trials and experiments

    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
    adors
    -0.07
    assi
    -0.07
    Drawable
    -0.06
    θÏħ
    -0.06
    inth
    -0.06
    elsing
    -0.06
    él
    -0.06
    FRING
    -0.06
     authorities
    -0.06
    ngth
    -0.06
    POSITIVE LOGITS
     involving
    0.07
     conducted
    0.07
    urtle
    0.06
     with
    0.06
    ATRIX
    0.06
    exec
    0.06
    .Dataset
    0.06
     withd
    0.06
     tém
    0.06
    ixe
    0.06
    Activations Density 0.036%

    No Known Activations