© 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. 29729
    Prev
    Next
    INDEX
    Explanations

    words related to names and titles

    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
    åĩĨ
    -0.07
    оÑħ
    -0.07
    hil
    -0.07
    ião
    -0.07
    agus
    -0.07
    ocker
    -0.06
    é¦ĸ页
    -0.06
     tant
    -0.06
    oux
    -0.06
    ocities
    -0.06
    POSITIVE LOGITS
    cher
    0.07
    ails
    0.06
    elda
    0.06
    zek
    0.06
    yp
    0.06
     tá»Ń
    0.06
    eln
    0.06
    apan
    0.06
     MPU
    0.06
    mir
    0.06
    Activations Density 0.016%

    No Known Activations