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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96199
    Prev
    Next
    INDEX
    Explanations

    ingredients or components commonly associated with food or medication

    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
    lias
    -0.08
    247
    -0.07
    lamaz
    -0.07
    uard
    -0.07
    lish
    -0.07
     hour
    -0.06
    iris
    -0.06
    778
    -0.06
    airy
    -0.06
    404
    -0.06
    POSITIVE LOGITS
    jte
    0.06
     Paren
    0.06
    obl
    0.06
    ativity
    0.06
     grosse
    0.06
    äºī
    0.05
     jerk
    0.05
    æ£ļ
    0.05
    опÑĢи
    0.05
    ief
    0.05
    Activations Density 0.002%

    No Known Activations