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. 5-LLAMASCOPE-RES-32K
    6. 18095
    Prev
    Next
    INDEX
    Explanations

    terms related to job market statistics and employment trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orsch
    -0.17
    agan
    -0.17
    ª
    -0.16
    İ
    -0.15
    ħ
    -0.15
    acey
    -0.14
    ignKey
    -0.14
    otec
    -0.14
     sour
    -0.14
    entionPolicy
    -0.14
    POSITIVE LOGITS
    imbus
    0.15
    chas
    0.14
    ypy
    0.14
    DTV
    0.14
    emploi
    0.14
     FIELD
    0.14
    lessly
    0.14
    ±Ð¾ÑĤ
    0.14
    odyn
    0.14
    azon
    0.13
    Activations Density 0.101%

    No Known Activations