© 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. 119574
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "quick to point out."

    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
     Ekon
    -0.08
     Lage
    -0.07
    dda
    -0.07
    adam
    -0.07
    .scalablytyped
    -0.07
    kuk
    -0.07
    ì¸ł
    -0.07
    ëł´
    -0.07
     trá»ĭ
    -0.07
    ERN
    -0.06
    POSITIVE LOGITS
    zeitig
    0.06
     noticed
    0.06
    oes
    0.06
     replen
    0.06
    imers
    0.06
    bsp
    0.06
    (er
    0.05
    '=>['
    0.05
    inded
    0.05
     onset
    0.05
    Activations Density 0.009%

    No Known Activations