© 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. 106911
    Prev
    Next
    INDEX
    Explanations

    references to notable events and speeches involving public figures and political controversies

    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
    iros
    -0.07
    aban
    -0.06
    akis
    -0.06
    avern
    -0.06
    esome
    -0.06
    alley
    -0.06
     intuitive
    -0.06
    andom
    -0.06
     Stam
    -0.06
    688
    -0.06
    POSITIVE LOGITS
     speakers
    0.10
     speaker
    0.09
    -spe
    0.08
     cancellation
    0.08
     Speakers
    0.08
    Cancelled
    0.07
    _sock
    0.07
    speaker
    0.07
    aÄį
    0.07
     speaking
    0.07
    Activations Density 0.008%

    No Known Activations