© 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 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. 29176
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating supplementary features or offers

    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
     ifndef
    -0.06
    ÙĪÛĮس
    -0.06
    morgan
    -0.06
    duit
    -0.06
    osc
    -0.06
    _hz
    -0.06
    idges
    -0.06
    .cf
    -0.06
     darm
    -0.06
     вд
    -0.06
    POSITIVE LOGITS
     rem
    0.07
    assin
    0.06
    _tC
    0.06
    316
    0.06
    /null
    0.06
    ç»Ń
    0.06
    eff
    0.05
    fd
    0.05
    ST
    0.05
     incon
    0.05
    Activations Density 0.000%

    No Known Activations