© 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. 5-LLAMASCOPE-RES-131K
    11. 126612
    Prev
    Next
    INDEX
    Explanations

    terms related to user interactions with interfaces

    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
    egrator
    -0.08
    ìĸ¼
    -0.07
    Æ°á»Ľi
    -0.07
    pig
    -0.06
    OPLE
    -0.06
    imers
    -0.06
    浦
    -0.06
    Ậ
    -0.06
    saldo
    -0.06
    /div
    -0.06
    POSITIVE LOGITS
    anks
    0.07
    ail
    0.07
    nez
    0.06
    ว
    0.06
    illet
    0.06
     Wanna
    0.06
    ãĥ³ãĥĦ
    0.06
     cues
    0.06
    mma
    0.06
     Crus
    0.06
    Activations Density 0.000%

    No Known Activations