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. 21-LLAMASCOPE-RES-32K
    6. 9990
    Prev
    Next
    INDEX
    Explanations

    references to films, music, and cultural events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .nih
    -0.16
    stdafx
    -0.16
    razier
    -0.15
    rink
    -0.14
    .examples
    -0.14
    รม
    -0.14
    ered
    -0.13
    enou
    -0.13
     Kirk
    -0.13
    uish
    -0.13
    POSITIVE LOGITS
    jar
    0.17
    .AR
    0.17
     Tar
    0.16
     jar
    0.16
    arf
    0.15
     MAR
    0.15
    å¢
    0.15
     UIBar
    0.15
     bart
    0.15
    Tar
    0.15
    Activations Density 0.083%

    No Known Activations