© 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. 76668
    Prev
    Next
    INDEX
    Explanations

    structured programming constructs, particularly braces or brackets

    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
    LV
    -0.07
    lico
    -0.07
    eed
    -0.07
    XL
    -0.07
     Erotische
    -0.06
    ife
    -0.06
    noop
    -0.06
    Ïĥι
    -0.06
    agger
    -0.06
    NG
    -0.06
    POSITIVE LOGITS
    -scrollbar
    0.06
    ìĽħ
    0.06
    бÑĢа
    0.06
     Alb
    0.06
     pic
    0.06
    Haz
    0.06
    Brains
    0.06
    ButtonText
    0.06
    .disc
    0.06
     calend
    0.05
    Activations Density 0.000%

    No Known Activations