© 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. 54073
    Prev
    Next
    INDEX
    Explanations

    social media engagement prompts

    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
    ousel
    -0.07
    FindBy
    -0.07
    ",__
    -0.07
    sic
    -0.06
    awe
    -0.06
    ô
    -0.06
     Fang
    -0.06
     Dude
    -0.06
    ildo
    -0.06
    Ń
    -0.06
    POSITIVE LOGITS
     Nightmare
    0.06
     ob
    0.06
    ipo
    0.06
    ob
    0.06
     Rip
    0.06
    ijn
    0.06
     ÑĢазви
    0.06
    OB
    0.06
    rar
    0.06
    èĪĪ
    0.06
    Activations Density 0.000%

    No Known Activations