© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56869
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting characters in code or markup

    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
    arti
    -0.07
    zial
    -0.07
    çĥ
    -0.07
    andon
    -0.07
    culus
    -0.07
    DSA
    -0.07
    ÙĪز
    -0.06
    achs
    -0.06
    enton
    -0.06
    @$
    -0.06
    POSITIVE LOGITS
    meer
    0.07
    hei
    0.06
     (()
    0.06
    vel
    0.06
    éĺħ读次æķ°
    0.06
    grow
    0.06
    èĤ²
    0.06
    qh
    0.06
    nal
    0.06
    ãĨ
    0.05
    Activations Density 0.001%

    No Known Activations