© 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. 126290
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting marks, indicating structure in the 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
    ants
    -0.07
    reste
    -0.06
    .Cursors
    -0.06
    antd
    -0.06
    ãĥIJãĤ¤
    -0.06
    Ñħов
    -0.06
    ète
    -0.06
    licht
    -0.06
     dest
    -0.06
    /met
    -0.06
    POSITIVE LOGITS
    atsu
    0.07
    ÏĩÏģι
    0.06
     clearColor
    0.06
    AccessType
    0.06
    .usermodel
    0.06
    Syntax
    0.06
    evi
    0.06
    보기
    0.06
     createState
    0.06
    frey
    0.06
    Activations Density 0.008%

    No Known Activations