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. 7-LLAMASCOPE-RES-32K
    6. 13749
    Prev
    Next
    INDEX
    Explanations

    programming and data structure-related keywords

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EventManager
    -0.16
    oze
    -0.15
    ãģĭãģij
    -0.14
    برد
    -0.14
     Liquid
    -0.14
    kus
    -0.14
    fuse
    -0.14
    ismet
    -0.14
    acho
    -0.14
    _float
    -0.14
    POSITIVE LOGITS
    Wunused
    0.16
    akk
    0.15
    KIT
    0.15
     SITE
    0.15
    .chunk
    0.14
    769
    0.14
    798
    0.14
    777
    0.14
    URY
    0.13
    طاÙĨ
    0.13
    Activations Density 0.022%

    No Known Activations