© 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. 91602
    Prev
    Next
    INDEX
    Explanations

    expressions of awareness or knowledge

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    rawn
    -0.06
    ailability
    -0.06
    roperties
    -0.06
     conformity
    -0.06
    ournée
    -0.06
    214
    -0.06
    egra
    -0.06
    unted
    -0.05
     chained
    -0.05
    TIM
    -0.05
    POSITIVE LOGITS
    anst
    0.07
    _PIPELINE
    0.07
    hill
    0.07
    rix
    0.06
    HIR
    0.06
    ape
    0.06
    oxide
    0.06
    estar
    0.06
    ÄŁinden
    0.06
    é«ĺéĢŁ
    0.06
    Activations Density 0.039%

    No Known Activations