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. 16871
    Prev
    Next
    INDEX
    Explanations

    roles related to healthcare professions and technical support in medical settings

    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
    人çī©
    -0.17
    altar
    -0.15
    -Methods
    -0.14
    ilden
    -0.14
     perÃŃ
    -0.14
    otime
    -0.14
    .Foundation
    -0.14
    åĶĩ
    -0.14
    heiten
    -0.14
    Unknown
    -0.14
    POSITIVE LOGITS
     profession
    0.19
    rix
    0.19
     assistants
    0.19
    ittel
    0.19
     cum
    0.18
    ural
    0.17
     salary
    0.17
    ess
    0.17
    513
    0.17
     assistant
    0.16
    Activations Density 0.201%

    No Known Activations