© 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. 116745
    Prev
    Next
    INDEX
    Explanations

    concepts related to returning or revisiting places or experiences

    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
    avern
    -0.08
    abei
    -0.07
    oplast
    -0.07
    Å¡ov
    -0.06
    afil
    -0.06
    ë¹ĦìķĦ
    -0.06
    :variables
    -0.06
    amon
    -0.06
    ulong
    -0.06
     Replacement
    -0.06
    POSITIVE LOGITS
     repeat
    0.14
     repetition
    0.12
     Repeat
    0.12
     repeats
    0.11
     повÑĤоÑĢ
    0.11
    Repeat
    0.11
     future
    0.11
    repeat
    0.10
     recurrence
    0.10
    .repeat
    0.10
    Activations Density 0.064%

    No Known Activations