© 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. 92181
    Prev
    Next
    INDEX
    Explanations

    references to conflict and physical confrontation

    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
    serde
    -0.08
    วà¸Ļ
    -0.08
    azer
    -0.08
    odÃŃ
    -0.08
    ì§ĢëıĦ
    -0.07
    inea
    -0.07
    Ä°s
    -0.07
    ë¥
    -0.07
    sink
    -0.07
    Scalars
    -0.07
    POSITIVE LOGITS
     so
    0.06
     ahead
    0.06
     animal
    0.06
     erg
    0.06
     their
    0.06
     therefore
    0.06
     thus
    0.05
     overnight
    0.05
     or
    0.05
     hence
    0.05
    Activations Density 0.004%

    No Known Activations