© 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. 9-LLAMASCOPE-RES-131K
    11. 95497
    Prev
    Next
    INDEX
    Explanations

    phrases and patterns related to statistics and player 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
    mium
    -0.07
    atin
    -0.07
    uros
    -0.06
    arters
    -0.06
    æĸ
    -0.06
     seedu
    -0.06
    erah
    -0.06
    ÑĮÑİ
    -0.06
    abis
    -0.06
    SI
    -0.06
    POSITIVE LOGITS
    gis
    0.07
    μεν
    0.07
    orest
    0.07
    .Theme
    0.06
    baz
    0.06
    _courses
    0.06
    ılım
    0.06
    ISTER
    0.06
    kers
    0.06
     HAS
    0.06
    Activations Density 0.010%

    No Known Activations