© 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. 57118
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Liz."

    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
    ุม
    -0.07
    iyan
    -0.07
    Å¡ti
    -0.07
    stown
    -0.07
    aler
    -0.06
    cete
    -0.06
    esimal
    -0.06
    ipa
    -0.06
    .elementAt
    -0.06
    ยà¸Ļà¸ķ
    -0.06
    POSITIVE LOGITS
    beth
    0.11
    zy
    0.10
    abet
    0.07
    finity
    0.07
    zi
    0.07
    abelle
    0.07
    y
    0.07
    bie
    0.07
    hou
    0.07
    lessly
    0.07
    Activations Density 0.002%

    No Known Activations