© 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. 1844
    Prev
    Next
    INDEX
    Explanations

    evaluations of character, particularly in relation to negative labeling and moral judgments

    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
    PFN
    -0.09
    ãģŀ
    -0.08
    ãĥĪãĥª
    -0.08
    ellas
    -0.07
    ãģ£ãģ¨
    -0.07
    RCT
    -0.07
    ANNEL
    -0.07
    ozor
    -0.07
    _heads
    -0.07
    DCF
    -0.07
    POSITIVE LOGITS
     hero
    0.07
     heroine
    0.06
     heroes
    0.06
     trait
    0.06
     Baby
    0.06
    rite
    0.06
     stabil
    0.06
     enemy
    0.06
    asion
    0.06
     Hero
    0.05
    Activations Density 0.066%

    No Known Activations