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. 96037
    Prev
    Next
    INDEX
    Explanations

    statistical percentages related to data or rankings

    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
    aveled
    -0.07
    egie
    -0.07
    ilon
    -0.07
    ibel
    -0.06
    afil
    -0.06
    obao
    -0.06
    à¸Ļà¸ģ
    -0.06
    zman
    -0.06
    stdbool
    -0.06
    asad
    -0.06
    POSITIVE LOGITS
     resil
    0.07
    estic
    0.06
    _CN
    0.06
     dư
    0.06
    rain
    0.06
    .Usage
    0.06
    rac
    0.06
    ,proto
    0.06
     Heard
    0.06
    ãĥ¬ãĤ¤
    0.06
    Activations Density 0.009%

    No Known Activations