© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31197
    Prev
    Next
    INDEX
    Explanations

    phrases related to manipulation and controversial political claims

    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
    è³¢
    -0.07
    ueur
    -0.07
     hâl
    -0.07
    theid
    -0.07
    /gin
    -0.06
     character
    -0.06
    ekil
    -0.06
    cent
    -0.06
    robe
    -0.06
    HT
    -0.06
    POSITIVE LOGITS
    inton
    0.06
    iggers
    0.06
     FUCK
    0.06
     nationwide
    0.06
     Fuck
    0.06
    
    0.06
    iddles
    0.06
    bern
    0.06
     sleeper
    0.06
    ượng
    0.06
    Activations Density 0.000%

    No Known Activations