© 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. 76174
    Prev
    Next
    INDEX
    Explanations

    mentions of long-term residence or duration in specific 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
    agher
    -0.07
    uler
    -0.07
    idd
    -0.06
    ibt
    -0.06
    .ide
    -0.06
    ábado
    -0.06
    ait
    -0.06
    igan
    -0.06
     precursor
    -0.06
    anos
    -0.06
    POSITIVE LOGITS
     пÑĢож
    0.06
    /commons
    0.06
     family
    0.06
    esson
    0.06
    672
    0.06
     Irma
    0.06
     corporate
    0.06
    urm
    0.06
    unal
    0.06
     lifestyle
    0.06
    Activations Density 0.014%

    No Known Activations