© 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. 74717
    Prev
    Next
    INDEX
    Explanations

    elements and features related to product descriptions

    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
    anches
    -0.06
    jian
    -0.06
    acro
    -0.06
    adt
    -0.06
     faced
    -0.06
    aby
    -0.05
    cona
    -0.05
     improvised
    -0.05
     eventually
    -0.05
     ing
    -0.05
    POSITIVE LOGITS
     already
    0.20
     Already
    0.20
    already
    0.19
    Already
    0.18
     ready
    0.17
     sẵn
    0.17
    ready
    0.16
     READY
    0.15
     bereits
    0.15
    _already
    0.14
    Activations Density 0.122%

    No Known Activations