© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 23766
    Prev
    Next
    INDEX
    Explanations

    key fields and parameters related to a structured data schema or configuration settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :'
    -0.20
    :'↵
    -0.19
    ;'
    -0.18
    :',
    -0.17
    :')↵
    -0.16
    :"↵
    -0.15
    ;,
    -0.15
    /'
    -0.15
    :)
    -0.15
    ï¼Į“
    -0.15
    POSITIVE LOGITS
    ":
    0.25
     ":
    0.17
    "}),↵
    0.17
    ':
    0.15
     ####
    0.15
    "=>
    0.15
    rido
    0.14
    \":
    0.14
    ï¼ģï¼ģ↵↵
    0.14
    aign
    0.14
    Activations Density 0.023%

    No Known Activations