© 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. 61292
    Prev
    Next
    INDEX
    Explanations

    references to boxes or container-like objects

    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
    uppe
    -0.09
    utomation
    -0.08
    бо
    -0.08
    ufs
    -0.08
    öz
    -0.07
    ovich
    -0.07
    udes
    -0.07
    ustrial
    -0.07
    inceton
    -0.07
     {*}
    -0.07
    POSITIVE LOGITS
    (es
    0.15
    tures
    0.10
    ses
    0.09
    <dyn
    0.08
    -sizing
    0.08
    es
    0.08
    plorer
    0.08
    esModule
    0.07
    .Box
    0.07
    (Box
    0.07
    Activations Density 0.022%

    No Known Activations