© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 12-LLAMASCOPE-RES-32K
    11. 29368
    Prev
    Next
    INDEX
    Explanations

    punctuation marks that end sentences

    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
    elle
    -0.14
    ingers
    -0.14
    essim
    -0.13
    ëĭī
    -0.13
     Twitch
    -0.13
     Kitt
    -0.13
    -transitional
    -0.13
    [e
    -0.13
     Durant
    -0.13
    utor
    -0.13
    POSITIVE LOGITS
    Compound
    0.14
    inion
    0.14
    éré
    0.14
    ãĥ¼ãĥł
    0.14
    compound
    0.14
    .swagger
    0.14
    peng
    0.13
    amiliar
    0.13
    aid
    0.13
    rian
    0.13
    Activations Density 0.059%

    No Known Activations