© 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. 128962
    Prev
    Next
    INDEX
    Explanations

    descriptions of housing options and amenities for diverse preferences

    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
     Rudd
    -0.07
    _WORLD
    -0.07
    ords
    -0.06
    atu
    -0.06
     cheek
    -0.06
    меÑĢик
    -0.06
     Rows
    -0.06
    cri
    -0.06
    python
    -0.06
    avras
    -0.06
    POSITIVE LOGITS
     options
    0.10
     ranging
    0.09
     range
    0.09
    options
    0.08
     variety
    0.08
     choices
    0.08
     Options
    0.08
     cater
    0.07
     OPTIONS
    0.07
     Choose
    0.07
    Activations Density 0.167%

    No Known Activations