© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 1542
    Prev
    Next
    INDEX
    Explanations

    references to conflict and combat situations

    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
     æķħ
    -0.09
    еÑĢин
    -0.08
    igli
    -0.08
    रण
    -0.08
    -bodied
    -0.08
    _TestCase
    -0.07
    .ManyToMany
    -0.07
    ertest
    -0.07
    ileen
    -0.07
    éļIJ
    -0.07
    POSITIVE LOGITS
     ab
    0.06
     cant
    0.06
     downfall
    0.06
     fall
    0.06
     challenged
    0.05
     voluntarily
    0.05
     Operand
    0.05
    entar
    0.05
     Reform
    0.05
     opposite
    0.05
    Activations Density 0.097%

    No Known Activations