© 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. 2017
    Prev
    Next
    INDEX
    Explanations

    concepts related to understanding, persuasion, and military actions

    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
    fak
    -0.07
    Ñĥже
    -0.07
    μαÏĦο
    -0.06
    ÃĶNG
    -0.06
     prv
    -0.06
    ordova
    -0.06
     stav
    -0.06
    ">//
    -0.06
    ãĥ³ãĥĨãĤ£
    -0.06
    यर
    -0.06
    POSITIVE LOGITS
     .↵
    0.07
    ckill
    0.07
     .↵↵
    0.07
     ,
    0.07
     [=
    0.06
     .č↵
    0.06
     meaning
    0.06
    _exempt
    0.06
    DebugEnabled
    0.06
    acre
    0.06
    Activations Density 0.020%

    No Known Activations