© 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. 18781
    Prev
    Next
    INDEX
    Explanations

    language related to personal journeys and movements

    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
    åłĤ
    -0.09
    ché
    -0.07
    ëł
    -0.07
    ammad
    -0.07
    lica
    -0.07
    ubit
    -0.06
    åł
    -0.06
    edicine
    -0.06
    phia
    -0.06
    trip
    -0.06
    POSITIVE LOGITS
    移åĭķ
    0.09
    移åĬ¨
    0.09
     move
    0.09
     nom
    0.08
     moving
    0.08
    -move
    0.08
     ìĿ´ëıĻ
    0.08
    .move
    0.08
     wherever
    0.08
     MOVE
    0.08
    Activations Density 0.118%

    No Known Activations