© 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. 95887
    Prev
    Next
    INDEX
    Explanations

    the preposition "for" indicating purpose or benefit in various contexts

    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
    lessly
    -0.08
    epad
    -0.08
    errupt
    -0.07
    zung
    -0.07
    kd
    -0.06
    leet
    -0.06
    imated
    -0.06
    nova
    -0.06
    meer
    -0.06
    acz
    -0.06
    POSITIVE LOGITS
     example
    0.19
     instance
    0.14
     exemplo
    0.13
     ejemplo
    0.13
    example
    0.13
     Example
    0.12
     exemple
    0.12
     напÑĢимеÑĢ
    0.12
    Example
    0.11
    -example
    0.11
    Activations Density 0.020%

    No Known Activations