© 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. 87210
    Prev
    Next
    INDEX
    Explanations

    patterns of hypocrisy and double standards regarding political and social narratives

    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
    utin
    -0.06
    \views
    -0.06
    UBY
    -0.06
    Ïĥιο
    -0.06
    eldorf
    -0.06
    ÑĤÑĢон
    -0.06
    enko
    -0.06
     rightly
    -0.06
    vailability
    -0.05
    roupon
    -0.05
    POSITIVE LOGITS
     claim
    0.11
     claimed
    0.10
    pret
    0.10
     CLAIM
    0.10
     pret
    0.10
     claims
    0.10
     Claim
    0.10
     claiming
    0.09
    Claim
    0.09
     pretended
    0.09
    Activations Density 0.070%

    No Known Activations