© 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. 781
    Prev
    Next
    INDEX
    Explanations

    annotations related to programming or technical documentation

    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
    laÄį
    -0.07
     Courier
    -0.07
    ừng
    -0.07
    ìĥµ
    -0.06
    onda
    -0.06
    ÑĢив
    -0.06
    eldon
    -0.06
    hei
    -0.06
    aller
    -0.06
    istics
    -0.06
    POSITIVE LOGITS
    Dal
    0.06
    ALI
    0.06
    ARY
    0.06
     Hart
    0.06
    kker
    0.06
    ë°°
    0.06
    riminator
    0.06
    inky
    0.06
    iveau
    0.05
    182
    0.05
    Activations Density 0.000%

    No Known Activations