© 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. 95826
    Prev
    Next
    INDEX
    Explanations

    multiple occurrences of the word "following" and its related context within a structured document, especially in the context of presenting results, definitions, theorems, or lemmas

    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
     Tamb
    -0.08
    $MESS
    -0.07
    ugi
    -0.06
     inn
    -0.06
    )(__
    -0.06
    avy
    -0.06
    ZA
    -0.06
    aida
    -0.06
    eid
    -0.06
     Britt
    -0.06
    POSITIVE LOGITS
    IGGER
    0.07
     definition
    0.07
     statement
    0.06
    pus
    0.06
     facts
    0.06
    ycler
    0.06
    846
    0.06
     Facts
    0.06
     scenario
    0.06
    ijn
    0.06
    Activations Density 0.040%

    No Known Activations