© 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. 55958
    Prev
    Next
    INDEX
    Explanations

    elements related to variable declaration and initialization 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
     Chamber
    -0.06
    678
    -0.06
     Hud
    -0.06
    yw
    -0.06
    aeda
    -0.06
    olia
    -0.06
    Ú©ÛĮÙĦ
    -0.06
    غاز
    -0.06
     Sinclair
    -0.06
    undi
    -0.06
    POSITIVE LOGITS
    åı·
    0.08
     inclusive
    0.08
    reon
    0.07
    pler
    0.07
    inclusive
    0.07
     Rae
    0.07
    thag
    0.07
    _MARGIN
    0.07
    clusive
    0.07
    Reached
    0.07
    Activations Density 0.064%

    No Known Activations