© 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. 128866
    Prev
    Next
    INDEX
    Explanations

    references to death and related concepts

    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
    agit
    -0.07
    grily
    -0.07
    usto
    -0.07
    ynom
    -0.07
    VERR
    -0.07
    IFF
    -0.06
    odu
    -0.06
     Morrow
    -0.06
    olen
    -0.06
    URA
    -0.06
    POSITIVE LOGITS
    .FontStyle
    0.07
    LTR
    0.06
     after
    0.06
    ungen
    0.06
     before
    0.06
    ÅĻeh
    0.06
    OwnProperty
    0.06
    suppress
    0.06
     front
    0.06
    _hook
    0.06
    Activations Density 0.000%

    No Known Activations