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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 40208
    Prev
    Next
    INDEX
    Explanations

    terminology associated with relocation and moving services

    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
    ODB
    -0.08
    OMEM
    -0.08
    endon
    -0.07
    ocht
    -0.07
    lest
    -0.07
    ãĤĦãģĻ
    -0.06
    monds
    -0.06
    getAs
    -0.06
    iges
    -0.06
     åł
    -0.06
    POSITIVE LOGITS
    ylie
    0.06
    ampa
    0.06
     blues
    0.06
     fork
    0.06
     Stress
    0.06
    imulator
    0.06
    gren
    0.06
     stress
    0.06
    resar
    0.06
    ¢
    0.06
    Activations Density 0.010%

    No Known Activations