© 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. 3860
    Prev
    Next
    INDEX
    Explanations

    mentions of educational institutions and their related terms

    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
    ãģĬãĤĬ
    -0.09
    aters
    -0.08
    emple
    -0.07
    aurus
    -0.06
    cha
    -0.06
    olic
    -0.06
    cy
    -0.06
    еÑĢв
    -0.06
    awy
    -0.06
    extr
    -0.06
    POSITIVE LOGITS
    children
    0.12
    yard
    0.12
    boy
    0.11
    girls
    0.10
    girl
    0.10
    house
    0.10
    teachers
    0.09
    teacher
    0.09
    sWith
    0.09
    boys
    0.09
    Activations Density 0.056%

    No Known Activations