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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3576
    Prev
    Next
    INDEX
    Explanations

    Java package and import statements related to specific libraries

    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
    åIJ¯
    -0.06
    rung
    -0.06
    borough
    -0.06
    001
    -0.06
    mmc
    -0.05
     Provincial
    -0.05
    udi
    -0.05
    escort
    -0.05
    ough
    -0.05
     Britt
    -0.05
    POSITIVE LOGITS
    ást
    0.07
    INO
    0.07
    ino
    0.06
    agedList
    0.06
    esser
    0.06
    utch
    0.06
    ãĥ¼ãĥį
    0.06
    tsy
    0.06
    ánh
    0.06
    indow
    0.06
    Activations Density 0.008%

    No Known Activations