© 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 EvalsExportsinterp-engineNEWAPI 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. 105149
    Prev
    Next
    INDEX
    Explanations

    specific formatting or structure commonly associated with technical documents or mathematical expressions

    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
    xfa
    -0.06
    ÅĽ
    -0.06
     i
    -0.06
    /k
    -0.06
    fty
    -0.06
    bourg
    -0.06
    cona
    -0.06
     s
    -0.06
     fro
    -0.05
     S
    -0.05
    POSITIVE LOGITS
    30
    0.12
    31
    0.10
    29
    0.09
    33
    0.09
    27
    0.09
    36
    0.09
    35
    0.09
    32
    0.08
    34
    0.08
    26
    0.08
    Activations Density 0.081%

    No Known Activations