© 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. 17-LLAMASCOPE-RES-131K
    11. 89277
    Prev
    Next
    INDEX
    Explanations

    mentions of journalists and their work experience

    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
    欧ç¾İ
    -0.08
    mamak
    -0.08
    ajaran
    -0.08
    eniz
    -0.07
    SYM
    -0.07
    _EDEFAULT
    -0.07
    .tables
    -0.07
    меÑĪ
    -0.07
    .bp
    -0.07
    اÙĦÙī
    -0.07
    POSITIVE LOGITS
     hometown
    0.09
     small
    0.07
    small
    0.07
     newspapers
    0.06
     News
    0.06
    News
    0.06
     smaller
    0.06
    ello
    0.06
     reporters
    0.06
     Nachricht
    0.06
    Activations Density 0.013%

    No Known Activations