© 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. 9-LLAMASCOPE-RES-131K
    11. 94343
    Prev
    Next
    INDEX
    Explanations

    multiple types of punctuation marks and special characters

    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
     Lucas
    -0.07
    ptic
    -0.07
    verte
    -0.06
    isphere
    -0.06
    ochond
    -0.06
    opak
    -0.06
    essim
    -0.06
    roman
    -0.06
    ila
    -0.06
     Sloan
    -0.06
    POSITIVE LOGITS
     çĨ
    0.06
    /original
    0.06
    ãĥ¼ãĥĵ
    0.06
    éģķãģĦ
    0.06
    [__
    0.06
    iez
    0.06
     âĹĦ
    0.06
    cene
    0.06
    quential
    0.06
    ammers
    0.06
    Activations Density 0.001%

    No Known Activations