© 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. 14135
    Prev
    Next
    INDEX
    Explanations

    inquiries about trust and relationships

    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
    Ä±ÅŁÄ±k
    -0.08
    ucken
    -0.08
    367
    -0.07
    asing
    -0.07
    oir
    -0.07
    lon
    -0.07
    æĢģ
    -0.07
    ENTIC
    -0.07
     Surprise
    -0.07
    viron
    -0.07
    POSITIVE LOGITS
     enough
    0.07
     leave
    0.06
     permanently
    0.06
     overcome
    0.06
     Leave
    0.05
     outcome
    0.05
     deg
    0.05
     time
    0.05
     forever
    0.05
     Ultimately
    0.05
    Activations Density 0.012%

    No Known Activations