© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 118377
    Prev
    Next
    INDEX
    Explanations

    directives related to yard sales and property marketing

    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
    .Designer
    -0.08
    sgi
    -0.07
    ewart
    -0.07
    plx
    -0.07
    rnd
    -0.07
     GenerationType
    -0.06
    สม
    -0.06
    incare
    -0.06
    anela
    -0.06
    iglia
    -0.06
    POSITIVE LOGITS
    share
    0.06
     Neighborhood
    0.06
     neur
    0.06
     hedge
    0.06
    neighbor
    0.06
    plant
    0.06
    rol
    0.06
     neutrality
    0.06
     neighborhood
    0.06
     everybody
    0.06
    Activations Density 0.001%

    No Known Activations