© 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. 71116
    Prev
    Next
    INDEX
    Explanations

    sentiments and opinions regarding Welsh independence

    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
     roÄįnÃŃ
    -0.08
    swick
    -0.07
    ëı
    -0.07
    ÏĢι
    -0.07
    asser
    -0.07
    iam
    -0.07
     mastur
    -0.07
    anio
    -0.07
    .mit
    -0.06
    orex
    -0.06
    POSITIVE LOGITS
    emand
    0.06
    forme
    0.06
    pos
    0.06
     party
    0.06
     ASSIGN
    0.06
     Dro
    0.06
     Ips
    0.05
    èĬĻ
    0.05
    ithe
    0.05
     ÙħÙĤ
    0.05
    Activations Density 0.001%

    No Known Activations