© 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. 116410
    Prev
    Next
    INDEX
    Explanations

    specific codes or identifiers related to geographic or geological mapping

    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
    ãĥ³ãĥ
    -0.07
    emer
    -0.07
    &e
    -0.06
    amak
    -0.06
    ãĥ©ãĤ¹
    -0.06
    ickest
    -0.06
    prof
    -0.06
    amu
    -0.06
    _EXTENDED
    -0.06
    ivial
    -0.06
    POSITIVE LOGITS
    003
    0.10
    002
    0.09
    001
    0.09
    004
    0.08
    010
    0.08
    000
    0.08
    072
    0.08
    006
    0.08
    040
    0.08
    030
    0.07
    Activations Density 0.084%

    No Known Activations