© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 95679
    Prev
    Next
    INDEX
    Explanations

    terms related to commuting and transportation

    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
    afd
    -0.08
    eated
    -0.07
    overe
    -0.07
    ÑĪем
    -0.06
    ziej
    -0.06
    coma
    -0.06
    icap
    -0.06
    ivid
    -0.06
    ũi
    -0.06
    eum
    -0.06
    POSITIVE LOGITS
    ortal
    0.08
    invert
    0.07
    ogg
    0.07
    urs
    0.07
    ting
    0.07
    eting
    0.06
    tid
    0.06
     invert
    0.06
    ÙĪÛĮÙĨ
    0.06
    gap
    0.06
    Activations Density 0.003%

    No Known Activations