© 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. 15-LLAMASCOPE-RES-131K
    6. 27191
    Prev
    Next
    INDEX
    Explanations

    phrases that ask about the characteristics or qualities of something

    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
     ucwords
    -0.08
    пп
    -0.07
    /cop
    -0.07
    ando
    -0.07
    uet
    -0.07
    ЧеÑĢ
    -0.07
    ç«ĭãģ¦
    -0.06
    imple
    -0.06
    iev
    -0.06
    oothing
    -0.06
    POSITIVE LOGITS
     unique
    0.07
    usive
    0.07
     successful
    0.06
     Unique
    0.06
     Successful
    0.06
    dress
    0.06
    olley
    0.06
     uniquely
    0.06
    orer
    0.06
    Unique
    0.06
    Activations Density 0.008%

    No Known Activations