© 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. 125427
    Prev
    Next
    INDEX
    Explanations

    names of individuals, particularly in the context of accomplishments or contributions

    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
    ãĥ«ãĥķ
    -0.07
    roots
    -0.06
    vyk
    -0.06
    active
    -0.06
    alternative
    -0.06
    jad
    -0.06
    ze
    -0.06
    ãĥ¬ãĥĵ
    -0.06
    zi
    -0.06
     Aviv
    -0.06
    POSITIVE LOGITS
    dale
    0.08
    ing
    0.08
    er
    0.08
    s
    0.07
    anst
    0.07
    597
    0.07
    erk
    0.06
    ange
    0.06
    case
    0.06
    borough
    0.06
    Activations Density 0.027%

    No Known Activations