© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 60835
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize the concept of "everything" and its accessibility or comprehensiveness

    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
    heimer
    -0.07
    лаж
    -0.06
    ESA
    -0.06
    太éĥİ
    -0.06
    IPS
    -0.06
    YP
    -0.06
    leon
    -0.06
    ICO
    -0.06
     Preis
    -0.06
    rico
    -0.06
    POSITIVE LOGITS
    /loose
    0.07
    uml
    0.07
    _PADDING
    0.06
     Details
    0.06
     you
    0.06
    TypeInfo
    0.06
    zzo
    0.06
    rane
    0.06
    dns
    0.06
    erd
    0.06
    Activations Density 0.004%

    No Known Activations