© 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. 129193
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "In" followed by numeric values indicating the sections or paragraphs of a text

    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
    ocale
    -0.07
    оло
    -0.06
     ChÃŃ
    -0.06
    epam
    -0.06
    å°½
    -0.06
     Hamm
    -0.06
    ham
    -0.06
    olate
    -0.06
    uki
    -0.06
    legation
    -0.06
    POSITIVE LOGITS
    omba
    0.07
    ussen
    0.06
    aul
    0.06
    440
    0.06
     mrb
    0.06
    atum
    0.06
    gnore
    0.06
    \Block
    0.06
    iya
    0.06
    UIScrollView
    0.06
    Activations Density 0.048%

    No Known Activations