© 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. 3796
    Prev
    Next
    INDEX
    Explanations

    expressions related to feelings of alienation and a desire for belonging

    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
    аÑĤков
    -0.06
    apons
    -0.06
     Everywhere
    -0.06
     atIndex
    -0.06
    oral
    -0.06
     everywhere
    -0.06
    ispers
    -0.06
    nde
    -0.06
    breadcrumbs
    -0.06
     Ign
    -0.06
    POSITIVE LOGITS
     novelty
    0.09
     novel
    0.08
    foreign
    0.08
     Novel
    0.08
     nov
    0.07
     foreign
    0.07
    /welcome
    0.07
     Foreign
    0.07
     rarity
    0.07
     FOREIGN
    0.07
    Activations Density 0.025%

    No Known Activations