© 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. 119509
    Prev
    Next
    INDEX
    Explanations

    definitions and declarations of character arrays in programming code

    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
    423
    -0.07
    ÑĢеменно
    -0.07
    esel
    -0.07
    ForObject
    -0.07
    ektor
    -0.07
    afone
    -0.07
    ogue
    -0.07
    ellt
    -0.07
    aml
    -0.07
    appen
    -0.07
    POSITIVE LOGITS
    [][]
    0.06
    med
    0.06
    æĤŁ
    0.06
     Opr
    0.06
    []
    0.06
    _groups
    0.05
    aines
    0.05
    ampoo
    0.05
    ¿ł
    0.05
    riere
    0.05
    Activations Density 0.017%

    No Known Activations