© 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. 5087
    Prev
    Next
    INDEX
    Explanations

    mentions of fax numbers and fax-related information

    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
    stance
    -0.06
     ê
    -0.06
    -in
    -0.06
    pron
    -0.06
     Ung
    -0.05
    neh
    -0.05
     Merrill
    -0.05
    γνÏī
    -0.05
    ALI
    -0.05
     c
    -0.05
    POSITIVE LOGITS
     jadx
    0.09
    otel
    0.08
    خط
    0.08
    inta
    0.08
     Tits
    0.07
    iks
    0.07
    YSIS
    0.07
    osis
    0.07
    -REAL
    0.07
    essaging
    0.07
    Activations Density 0.004%

    No Known Activations