© 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. 93815
    Prev
    Next
    INDEX
    Explanations

    nested structures or formats in programming code

    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
    lte
    -0.06
    Unavailable
    -0.06
     devil
    -0.06
    ajas
    -0.06
     ink
    -0.06
    ajan
    -0.05
    eb
    -0.05
    iar
    -0.05
    753
    -0.05
     Chap
    -0.05
    POSITIVE LOGITS
    vla
    0.08
    ¯u
    0.08
    ëłĩ
    0.07
    uppe
    0.07
    hea
    0.07
    ispecies
    0.07
    ôm
    0.07
    #ac
    0.07
    _REPEAT
    0.07
    erval
    0.07
    Activations Density 0.023%

    No Known Activations