© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18405
    Prev
    Next
    INDEX
    Explanations

    adjectives and descriptive phrases that convey quality and creativity in writing

    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
     contrat
    -0.07
    lef
    -0.06
     ones
    -0.06
    ankind
    -0.06
    recover
    -0.06
    ober
    -0.06
    637
    -0.06
    ãĥĩãĥ«
    -0.06
     Calder
    -0.06
    _closure
    -0.06
    POSITIVE LOGITS
    iger
    0.08
     ç«
    0.07
     debut
    0.07
    ì¢ħ
    0.07
    ipo
    0.07
    ibble
    0.07
    rip
    0.06
    ãĤĬãģ¨
    0.06
    .br
    0.06
    ilon
    0.06
    Activations Density 0.014%

    No Known Activations