© 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. 9-LLAMASCOPE-RES-131K
    11. 95514
    Prev
    Next
    INDEX
    Explanations

    references to real estate agents and property developments

    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
     Shut
    -0.06
    erk
    -0.06
    ér
    -0.06
    UNIT
    -0.06
    ahoma
    -0.06
     Seam
    -0.05
    308
    -0.05
    duit
    -0.05
    anon
    -0.05
     redirect
    -0.05
    POSITIVE LOGITS
     Kurul
    0.07
    ÙħÙĪد
    0.07
    lerce
    0.07
    (LP
    0.06
    .Generated
    0.06
     ÙĦÙĥرة
    0.06
    ायन
    0.06
    _CHIP
    0.06
    idlo
    0.06
    cente
    0.06
    Activations Density 0.011%

    No Known Activations