© 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. 17-LLAMASCOPE-RES-131K
    11. 60513
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions related to sending flowers and condolences

    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
    idges
    -0.08
    .asc
    -0.08
    ãĤ¹ãĤ«
    -0.08
    á»ī
    -0.07
    ustos
    -0.07
    à¤Ĥà¤Ń
    -0.07
    .bz
    -0.07
    ứt
    -0.07
    PathParam
    -0.07
    è²´
    -0.07
    POSITIVE LOGITS
     flop
    0.06
    ancia
    0.05
    setup
    0.05
     setup
    0.05
    aka
    0.05
    æ¼
    0.05
    ocy
    0.05
     comfort
    0.05
     Arms
    0.05
    c
    0.05
    Activations Density 0.000%

    No Known Activations