© 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. 1-LLAMASCOPE-RES-32K
    11. 24334
    Prev
    Next
    INDEX
    Explanations

    concepts and descriptors related to intuitive experiences and understandings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istrat
    -0.14
    essa
    -0.14
    iker
    -0.14
    riends
    -0.14
    reta
    -0.14
    efs
    -0.14
    trand
    -0.14
     Hanson
    -0.13
    eldon
    -0.13
    iska
    -0.13
    POSITIVE LOGITS
    Collapse
    0.15
     اÙħر
    0.15
    zzo
    0.14
    ãĥ³ãĥĢ
    0.14
    ©
    0.14
    (æľ¨
    0.14
    428
    0.14
    .library
    0.14
    amos
    0.14
    ously
    0.13
    Activations Density 0.004%

    No Known Activations