© 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. 61110
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to programming or code structure

    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
    ิà¹Ĥ
    -0.08
    amarin
    -0.08
    LBL
    -0.07
    .scalablytyped
    -0.07
    .IsNullOr
    -0.07
    ابÛĮ
    -0.07
    ikk
    -0.07
    ourn
    -0.07
    .dsl
    -0.07
    à¥įयव
    -0.07
    POSITIVE LOGITS
    ittest
    0.06
    avad
    0.06
    ammad
    0.06
    ราà¸Ĭ
    0.06
    kh
    0.05
    910
    0.05
    adesh
    0.05
    otel
    0.05
     synerg
    0.05
     Pearce
    0.05
    Activations Density 0.012%

    No Known Activations