© 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. 3614
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to conversation and dialogue

    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
    ofday
    -0.08
    lessness
    -0.07
    printStats
    -0.07
    ertools
    -0.07
    lessly
    -0.07
    zsche
    -0.07
    èĥ
    -0.07
    pga
    -0.07
    lexport
    -0.07
    chyb
    -0.07
    POSITIVE LOGITS
    ative
    0.09
    ational
    0.08
    ©
    0.07
    dia
    0.07
    du
    0.07
    ailles
    0.07
    ohn
    0.06
    dale
    0.06
    ance
    0.06
    atively
    0.06
    Activations Density 0.007%

    No Known Activations