Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96026
    Prev
    Next
    INDEX
    Explanations

    programming-related data types and structures

    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
    bserv
    -0.07
    gage
    -0.07
    edo
    -0.07
    rogram
    -0.06
    umerator
    -0.06
    oure
    -0.06
    ì§ij
    -0.06
    ipa
    -0.06
    lsru
    -0.06
    HEAD
    -0.06
    POSITIVE LOGITS
    /Internal
    0.08
    cheng
    0.06
    uchen
    0.06
    ãĤ¯ãĤ»
    0.06
    .cx
    0.06
    antics
    0.06
    roduced
    0.06
    ãĥ³ãĤ¸
    0.06
     Cri
    0.06
    ORMAL
    0.06
    Activations Density 0.007%

    No Known Activations