Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 125724
    Prev
    Next
    INDEX
    Explanations

    patterns of communal or shared experiences and challenges

    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
    uracy
    -0.08
    Touches
    -0.07
    apiro
    -0.07
    unya
    -0.07
    pto
    -0.07
    GY
    -0.06
    .strict
    -0.06
     aray
    -0.06
    ocities
    -0.06
    stinence
    -0.06
    POSITIVE LOGITS
     tendency
    0.07
    ãģ°ãģĭãĤĬ
    0.07
     too
    0.07
     tend
    0.07
     tended
    0.06
     templ
    0.06
    neg
    0.06
    cales
    0.06
     prematurely
    0.06
     Kimber
    0.06
    Activations Density 0.030%

    No Known Activations