© 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. 83134
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities related to artworks or their creators

    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
    ires
    -0.07
    PWD
    -0.06
    rels
    -0.06
    ç´Ļ
    -0.06
    524
    -0.06
    ek
    -0.06
    enson
    -0.06
    ела
    -0.06
    erson
    -0.06
    pond
    -0.06
    POSITIVE LOGITS
    getic
    0.10
    ÑĢÑıд
    0.07
    GY
    0.06
    ipay
    0.06
    igans
    0.06
    asmus
    0.06
    dbe
    0.06
    ãĥ«ãĥķ
    0.06
    imore
    0.06
    lide
    0.06
    Activations Density 0.019%

    No Known Activations