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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-LLAMASCOPE-RES-131K
    6. 96154
    Prev
    Next
    INDEX
    Explanations

    key themes and concepts related to literature and literary analysis

    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
    etter
    -0.07
    ager
    -0.07
     Tuy
    -0.07
    zas
    -0.07
    atty
    -0.07
    ember
    -0.07
    ì§ģ
    -0.06
    uls
    -0.06
    earn
    -0.06
     Daly
    -0.06
    POSITIVE LOGITS
    umbo
    0.06
    .scheme
    0.06
    æĬµ
    0.06
    afi
    0.06
    ndl
    0.05
    κή
    0.05
    enza
    0.05
    ODEV
    0.05
    OUGH
    0.05
    bars
    0.05
    Activations Density 0.354%

    No Known Activations