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. 25-LLAMASCOPE-RES-32K
    6. 10744
    Prev
    Next
    INDEX
    Explanations

    mentions of upcoming events or publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rega
    -0.16
    ensch
    -0.15
    oko
    -0.14
    usz
    -0.13
    æĺŁæľŁ
    -0.13
     STDCALL
    -0.13
    -prepend
    -0.13
    ãģĤãĤĬãģĮãģ¨ãģĨ
    -0.13
    .sync
    -0.12
     overnight
    -0.12
    POSITIVE LOGITS
     upcoming
    0.91
     forthcoming
    0.85
     pending
    0.65
     coming
    0.62
     soon
    0.62
     impending
    0.60
     imminent
    0.57
    coming
    0.57
    soon
    0.57
    pending
    0.52
    Activations Density 0.396%

    No Known Activations