© 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. 15-LLAMASCOPE-RES-131K
    11. 88631
    Prev
    Next
    INDEX
    Explanations

    fragments of compound modifiers suggesting complexity or duality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Characters randomly selected from various positions within text, with no clear pattern linking their occurrence or context.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
     blank
    -0.06
    Ỽi
    -0.06
    APH
    -0.06
    amp
    -0.06
     split
    -0.05
     Stevenson
    -0.05
    ent
    -0.05
    hti
    -0.05
    sız
    -0.05
     trai
    -0.05
    POSITIVE LOGITS
    åįļ士
    0.07
    _tls
    0.07
    eyer
    0.07
    roscope
    0.07
    INLINE
    0.07
    ekler
    0.07
    adder
    0.07
    ryn
    0.07
    eya
    0.07
    achuset
    0.06
    Activations Density 0.000%

    No Known Activations