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

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 26688
    Prev
    Next
    INDEX
    Explanations

    key details about individuals involved in vehicle accidents, including their identities and conditions

    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
    åłĤ
    -0.07
    enen
    -0.07
    ab
    -0.07
    .openg
    -0.07
    illez
    -0.07
    /REC
    -0.07
     parach
    -0.06
    ders
    -0.06
    owitz
    -0.06
    ippo
    -0.06
    POSITIVE LOGITS
     ident
    0.06
     foreign
    0.06
     ekip
    0.06
     mắc
    0.06
    ownership
    0.06
    foreign
    0.06
    je
    0.05
     возÑĢаÑģÑĤ
    0.05
     bi
    0.05
     ownership
    0.05
    Activations Density 0.015%

    No Known Activations