© 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. 54916
    Prev
    Next
    INDEX
    Explanations

    phrases related to returning or revisiting content

    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
    arest
    -0.06
     pros
    -0.06
    ockey
    -0.06
    ugh
    -0.06
    udur
    -0.05
    .dateTime
    -0.05
     screenSize
    -0.05
    ãĤµãĥ¼
    -0.05
    tn
    -0.05
     stages
    -0.05
    POSITIVE LOGITS
    поÑĢ
    0.08
    lednÃŃ
    0.07
     bì
    0.07
    ÐĽÐĺ
    0.07
    izio
    0.07
    _interfaces
    0.07
    toi
    0.07
    ĨĴ
    0.07
    ErrorException
    0.07
    eum
    0.07
    Activations Density 0.000%

    No Known Activations