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. 22-LLAMASCOPE-RES-32K
    6. 20571
    Prev
    Next
    INDEX
    Explanations

    financial metrics and statistics related to transactions and activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (£
    -0.15
    ATAL
    -0.14
    _CLUSTER
    -0.13
    loff
    -0.13
    Fuse
    -0.13
    itored
    -0.13
    TagName
    -0.13
    fuse
    -0.13
    ulfilled
    -0.13
    UIL
    -0.13
    POSITIVE LOGITS
     nearly
    0.25
     more
    0.22
     almost
    0.21
     over
    0.20
     about
    0.20
     around
    0.20
     close
    0.19
     approximately
    0.19
     record
    0.19
     exactly
    0.19
    Activations Density 0.238%

    No Known Activations