© 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. 24-LLAMASCOPE-RES-32K
    11. 13182
    Prev
    Next
    INDEX
    Explanations

    references to specialized fields of study and qualifications in the legal and medical professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ook
    -0.14
    quia
    -0.14
    adoo
    -0.14
    inish
    -0.14
    IFORM
    -0.13
    antt
    -0.13
    loh
    -0.13
    vla
    -0.13
    ustum
    -0.13
    antal
    -0.13
    POSITIVE LOGITS
     discipline
    0.52
     branch
    0.45
     fields
    0.45
     field
    0.45
     Branch
    0.44
     Discipline
    0.42
     disciplines
    0.41
     areas
    0.41
     discipl
    0.40
     area
    0.39
    Activations Density 0.205%

    No Known Activations