© 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. 71207
    Prev
    Next
    INDEX
    Explanations

    references to resume keywords and job search strategies

    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
     Morrow
    -0.06
    esser
    -0.06
    Trivia
    -0.06
    ifton
    -0.06
    .hasMore
    -0.06
    BootApplication
    -0.06
    åİŁæľ¬
    -0.06
    uala
    -0.06
     ÐĿÑĸ
    -0.06
    uro
    -0.06
    POSITIVE LOGITS
     pinch
    0.08
     Pin
    0.07
     pin
    0.07
    Pin
    0.06
     è¢
    0.06
    ÑĢÑĥÑĩ
    0.06
    ÑĢÑĥ
    0.06
    obuf
    0.06
    ë¶
    0.06
     gag
    0.06
    Activations Density 0.004%

    No Known Activations