© 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. 77430
    Prev
    Next
    INDEX
    Explanations

    instances of political discourse and expressions of frustration related to governance

    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
    訴
    -0.09
    ÄĽ
    -0.07
    jes
    -0.07
    ány
    -0.07
    msgid
    -0.07
    zÃŃ
    -0.07
    affer
    -0.07
    หมาย
    -0.07
    rå
    -0.07
    ãĥ¼ãĤ
    -0.06
    POSITIVE LOGITS
     House
    0.08
     chamber
    0.08
     session
    0.08
     Commons
    0.07
     Parliament
    0.07
     parliament
    0.07
     Chamber
    0.07
     Mot
    0.07
     floor
    0.07
     chambers
    0.07
    Activations Density 0.014%

    No Known Activations