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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 82127
    Prev
    Next
    INDEX
    Explanations

    common adjectives that describe quality or value

    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
    ylan
    -0.07
    819
    -0.07
    íĤ
    -0.06
    851
    -0.06
     Monaco
    -0.06
    omon
    -0.06
    857
    -0.06
    abama
    -0.06
    isses
    -0.06
    /Foundation
    -0.06
    POSITIVE LOGITS
     sadd
    0.07
    aits
    0.06
    è¡Ĩ
    0.06
    SED
    0.06
    arend
    0.06
     autoload
    0.06
    one
    0.06
     exc
    0.06
     bless
    0.06
    γκα
    0.06
    Activations Density 0.010%

    No Known Activations