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. 12-LLAMASCOPE-RES-32K
    6. 19598
    Prev
    Next
    INDEX
    Explanations

    economic statistics related to taxation and income distribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é©
    -0.15
    alama
    -0.15
    Translations
    -0.14
     initials
    -0.14
    ropp
    -0.14
    illon
    -0.14
     BigNumber
    -0.14
    ÏĢοÏħÏģγ
    -0.14
    icari
    -0.14
    avir
    -0.14
    POSITIVE LOGITS
     Arb
    0.14
     working
    0.14
    aniu
    0.14
    ứa
    0.14
     workers
    0.14
     Experience
    0.14
     лÑİ
    0.13
    Ñģол
    0.13
     Hog
    0.13
     living
    0.13
    Activations Density 0.159%

    No Known Activations