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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 82531
    Prev
    Next
    INDEX
    Explanations

    references to travel and tourism-related locations

    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
    arda
    -0.06
    onth
    -0.06
    ASSES
    -0.06
    inkel
    -0.06
     Chad
    -0.06
    ãĥ©ãĥ¼
    -0.06
     QtCore
    -0.06
    é¾Ħ
    -0.05
    anio
    -0.05
    /goto
    -0.05
    POSITIVE LOGITS
    EFI
    0.07
     Hv
    0.07
    nit
    0.07
    jie
    0.07
    vip
    0.06
    yk
    0.06
    ìłĢ
    0.06
    лиÑĨ
    0.06
    ©
    0.06
    dur
    0.06
    Activations Density 0.007%

    No Known Activations