© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 42451
    Prev
    Next
    INDEX
    Explanations

    references to individuals' current positions or statuses

    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
    .scalablytyped
    -0.07
    essed
    -0.07
    ovice
    -0.07
    ÑĢава
    -0.07
    ibrary
    -0.07
    aleza
    -0.07
    åħ¬åijĬ
    -0.07
     골
    -0.07
    uin
    -0.06
    .bridge
    -0.06
    POSITIVE LOGITS
    called
    0.08
     called
    0.08
    aca
    0.07
     Called
    0.07
    agar
    0.07
     simply
    0.07
    acho
    0.07
    åı«
    0.06
    -called
    0.06
    572
    0.06
    Activations Density 0.040%

    No Known Activations