© 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. 15-LLAMASCOPE-RES-131K
    11. 90294
    Prev
    Next
    INDEX
    Explanations

    references to gaming content and related media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Text segments that appear in citations, references, titles, or formal attributions, often representing precise wording that needs to be accurately quoted or referenced.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     seins
    -0.08
    vail
    -0.07
    quelle
    -0.07
    chio
    -0.07
    Ãłm
    -0.07
    ساÙĨ
    -0.07
    indi
    -0.07
    код
    -0.07
    ookies
    -0.06
    .Reporting
    -0.06
    POSITIVE LOGITS
    641
    0.06
    ampton
    0.06
    532
    0.06
    dent
    0.06
    GMEM
    0.06
    ová
    0.05
    dd
    0.05
    OwnProperty
    0.05
    t
    0.05
     Denn
    0.05
    Activations Density 0.013%

    No Known Activations