Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 43696
    Prev
    Next
    INDEX
    Explanations

    references to trips or travel experiences

    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
    erdem
    -0.08
    erde
    -0.07
     fitte
    -0.07
    vents
    -0.07
    ấp
    -0.07
    ermo
    -0.07
    erne
    -0.06
    rung
    -0.06
    tainment
    -0.06
    emple
    -0.06
    POSITIVE LOGITS
    advisor
    0.14
    licate
    0.14
     abroad
    0.12
     into
    0.12
    ods
    0.11
     to
    0.11
     down
    0.11
     home
    0.10
     away
    0.10
     south
    0.10
    Activations Density 0.020%

    No Known Activations