© 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. 15-LLAMASCOPE-RES-131K
    11. 103953
    Prev
    Next
    INDEX
    Explanations

    phrases indicating denial or dismissal of accountability

    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
    è¬
    -0.08
    mouseleave
    -0.07
    uart
    -0.07
     hete
    -0.07
    .scalablytyped
    -0.07
    URY
    -0.07
    defgroup
    -0.07
    orgia
    -0.07
    overn
    -0.07
    interop
    -0.07
    POSITIVE LOGITS
     really
    0.07
     anymore
    0.06
    really
    0.06
     Really
    0.06
    Really
    0.06
     actually
    0.06
    emie
    0.05
    681
    0.05
     fatt
    0.05
    awk
    0.05
    Activations Density 0.028%

    No Known Activations