© 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. 15-LLAMASCOPE-RES-131K
    11. 104080
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to the ability to attach or detach items

    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
    anan
    -0.07
     trh
    -0.06
    _alive
    -0.06
    ago
    -0.06
    vang
    -0.06
     tremend
    -0.06
     sor
    -0.06
    jte
    -0.06
    gh
    -0.06
    cki
    -0.06
    POSITIVE LOGITS
    á»ĭp
    0.07
    ilyn
    0.07
    /embed
    0.06
    ?p
    0.06
    /rem
    0.06
    690
    0.06
    /disable
    0.06
    \Php
    0.06
    obo
    0.06
    remove
    0.06
    Activations Density 0.004%

    No Known Activations