© 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. 119520
    Prev
    Next
    INDEX
    Explanations

    phrases related to understanding and interpretation

    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
    atten
    -0.07
    quam
    -0.07
    elden
    -0.07
    anship
    -0.07
    AXB
    -0.07
    laz
    -0.07
    jal
    -0.07
    awa
    -0.07
    ạ
    -0.07
    .RightToLeft
    -0.07
    POSITIVE LOGITS
    äºĭæ¥Ń
    0.07
    encion
    0.06
    nock
    0.06
     things
    0.06
    ItemSelected
    0.06
     Aç
    0.06
    strup
    0.05
     Liv
    0.05
    æ¢
    0.05
    meg
    0.05
    Activations Density 0.005%

    No Known Activations