© 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. 1272
    Prev
    Next
    INDEX
    Explanations

    names of individuals and their associations in a collaborative context

    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
    (EXPR
    -0.07
    uja
    -0.07
    parer
    -0.07
    ikat
    -0.07
    ofday
    -0.07
    èĨ
    -0.06
    Ç
    -0.06
     decorate
    -0.06
    à¸ļาล
    -0.06
    mpar
    -0.06
    POSITIVE LOGITS
     Orc
    0.06
     som
    0.06
     saturn
    0.06
    SenderId
    0.06
     conc
    0.06
     liter
    0.05
     Nur
    0.05
    antor
    0.05
     grounding
    0.05
    бÑĥ
    0.05
    Activations Density 0.009%

    No Known Activations