© 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. 70022
    Prev
    Next
    INDEX
    Explanations

    phone numbers formatted as a sequence of digits

    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
    lej
    -0.07
    REFERRED
    -0.07
    owie
    -0.06
    ipa
    -0.06
    statt
    -0.06
    çĽĸ
    -0.06
    agnostic
    -0.06
    seau
    -0.06
    ffe
    -0.06
     Loren
    -0.06
    POSITIVE LOGITS
     Ner
    0.07
    ofday
    0.07
    ìŀĸ
    0.07
     Gratuit
    0.07
    Scalars
    0.06
    اÙĪÙĩ
    0.06
     èIJ
    0.06
    $LANG
    0.06
    .glide
    0.06
    "is
    0.06
    Activations Density 0.007%

    No Known Activations