© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 74383
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "walked into" or similar expressions related to entering spaces or situations

    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
    ledge
    -0.07
    езд
    -0.07
    lauf
    -0.06
    amentos
    -0.06
    izu
    -0.06
    orio
    -0.06
    تÙĪر
    -0.06
    паÑĤ
    -0.06
    /inc
    -0.06
    fts
    -0.06
    POSITIVE LOGITS
    elix
    0.08
    prises
    0.07
    rz
    0.06
    ultiply
    0.06
    ĵĺ
    0.06
     vÃło
    0.06
    woods
    0.06
     bumper
    0.06
    SPAN
    0.06
     Lup
    0.06
    Activations Density 0.016%

    No Known Activations