© 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. 80879
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "go back" and its variations

    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
    appa
    -0.08
    chap
    -0.07
    astle
    -0.07
    Forge
    -0.06
     Dre
    -0.06
    982
    -0.06
    688
    -0.06
     lên
    -0.06
    ÙĬÙĥÙĬ
    -0.06
    inz
    -0.06
    POSITIVE LOGITS
    /fwlink
    0.07
     geschichten
    0.07
    nod
    0.07
     огÑĢа
    0.07
    temps
    0.07
     ÏĥÏĩ
    0.07
     ragaz
    0.06
    nak
    0.06
    elon
    0.06
    PROTO
    0.06
    Activations Density 0.005%

    No Known Activations