© 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. 753
    Prev
    Next
    INDEX
    Explanations

    expressions of concern or critique regarding social or political issues

    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
    uen
    -0.07
    ignKey
    -0.07
    roperty
    -0.07
    ende
    -0.07
    ulk
    -0.06
    IBE
    -0.06
    hausen
    -0.06
    abus
    -0.06
    indsight
    -0.06
    Ù©
    -0.06
    POSITIVE LOGITS
     lately
    0.12
     recently
    0.10
     recent
    0.08
     Recently
    0.08
    æľĢè¿ij
    0.08
    recent
    0.08
    Recently
    0.07
     newly
    0.06
     heels
    0.06
    .tm
    0.06
    Activations Density 0.068%

    No Known Activations