© 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. 105609
    Prev
    Next
    INDEX
    Explanations

    HTML or web-related content specifically involving targets and links

    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
    ollo
    -0.07
    ÑģоÑĢ
    -0.07
    isas
    -0.07
    ocab
    -0.06
    LEGRO
    -0.06
    isÃŃ
    -0.06
    .AutoComplete
    -0.06
    ÚĨÛĮ
    -0.06
    oen
    -0.06
    ãĥ³ãĥĨãĤ£
    -0.06
    POSITIVE LOGITS
     Ple
    0.06
    ebi
    0.06
     Worm
    0.06
    bp
    0.06
    azers
    0.06
    adil
    0.06
    ipline
    0.06
     pin
    0.06
    147
    0.06
    uje
    0.06
    Activations Density 0.000%

    No Known Activations