© 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. 5-LLAMASCOPE-RES-131K
    11. 126395
    Prev
    Next
    INDEX
    Explanations

    terms related to accountability and critique of authority

    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
     Cav
    -0.06
     shoe
    -0.06
    resh
    -0.06
     sho
    -0.06
     cav
    -0.06
    иÑĤа
    -0.06
     Tone
    -0.06
     Mills
    -0.06
    ponce
    -0.06
    styl
    -0.06
    POSITIVE LOGITS
    ahr
    0.08
    ÄĽn
    0.07
    arov
    0.07
    081
    0.07
    bpp
    0.07
     sobie
    0.07
    anger
    0.06
    acios
    0.06
    bk
    0.06
    éru
    0.06
    Activations Density 0.000%

    No Known Activations