© 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. 95857
    Prev
    Next
    INDEX
    Explanations

    affirmations and expressions of certainty

    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
    Nonce
    -0.08
    mada
    -0.07
    acker
    -0.06
    çĦ
    -0.06
    pp
    -0.06
    èŃľ
    -0.06
    acula
    -0.05
     tricks
    -0.05
     mnemonic
    -0.05
     trick
    -0.05
    POSITIVE LOGITS
    ialog
    0.08
    ergus
    0.08
    leDb
    0.07
    ÑĪкÑĥ
    0.07
    -Token
    0.07
    okie
    0.07
    elle
    0.07
     includ
    0.07
    yntax
    0.07
    escription
    0.07
    Activations Density 0.004%

    No Known Activations