© 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. 106858
    Prev
    Next
    INDEX
    Explanations

    words that indicate action, transformation, or development

    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
    Ìģc
    -0.07
    ucer
    -0.07
    ARGIN
    -0.07
    ÅĤo
    -0.06
    lessly
    -0.06
    éĬ
    -0.06
    ÑģÑĤÑĮ
    -0.06
    ειÏĤ
    -0.06
    üle
    -0.06
    kker
    -0.06
    POSITIVE LOGITS
    ing
    0.57
    ING
    0.31
    ingt
    0.21
    ting
    0.21
    ning
    0.18
    ingen
    0.17
    ging
    0.17
    ãĥ³ãĤ°
    0.16
    ming
    0.15
    ë§ģ
    0.15
    Activations Density 0.220%

    No Known Activations