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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-32K
    6. 9949
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jadx
    -0.16
    .timeScale
    -0.15
    groundColor
    -0.14
     molec
    -0.13
    bard
    -0.12
    ุà¹Ī
    -0.12
    MemoryWarning
    -0.12
     åĤ
    -0.12
     ilan
    -0.12
    frage
    -0.12
    POSITIVE LOGITS
     talking
    0.26
     Talking
    0.26
    Talking
    0.23
    Caption
    0.23
     Net
    0.22
     similarly
    0.20
     Caption
    0.20
     talks
    0.20
     Likewise
    0.20
     Know
    0.19
    Activations Density 0.014%

    No Known Activations