© 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. 78336
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate transitions or changes

    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
    alo
    -0.07
    çĶĺ
    -0.07
    ding
    -0.06
    eq
    -0.06
    ea
    -0.06
    Parms
    -0.06
    Cow
    -0.06
    qx
    -0.06
    zes
    -0.06
    weit
    -0.06
    POSITIVE LOGITS
     adulthood
    0.07
    /from
    0.07
     mode
    0.07
     another
    0.06
    arians
    0.06
    HI
    0.06
     sembl
    0.06
    кÑĤа
    0.06
     Advoc
    0.06
     Mode
    0.06
    Activations Density 0.029%

    No Known Activations