© 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. 1646
    Prev
    Next
    INDEX
    Explanations

    symbols and notations typically used in structured data 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
    gth
    -0.08
    ABCDEFG
    -0.07
    ABCDEFGHI
    -0.07
    евÑĸ
    -0.07
    clearfix
    -0.07
    ¦¬
    -0.07
    .recycle
    -0.07
    ingleton
    -0.07
    irthday
    -0.07
    enberg
    -0.07
    POSITIVE LOGITS
    iest
    0.06
    pn
    0.06
    aller
    0.05
    ~
    0.05
    -ing
    0.05
    -O
    0.05
    iol
    0.05
     stagger
    0.05
     té
    0.05
     Glam
    0.05
    Activations Density 0.027%

    No Known Activations