© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 18825
    Prev
    Next
    INDEX
    Explanations

    names and affiliations of individuals, particularly in artistic and academic contexts

    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
    acion
    -0.19
     Chavez
    -0.18
    iores
    -0.16
    reon
    -0.16
    缤
    -0.15
    ooks
    -0.15
     Staten
    -0.14
     Stacy
    -0.14
     aph
    -0.14
    adelphia
    -0.14
    POSITIVE LOGITS
     Fern
    0.24
     Mart
    0.23
     Torrent
    0.23
    Torrent
    0.21
     Cases
    0.19
     Gin
    0.19
     Juli
    0.18
    adÃŃ
    0.18
     Belmont
    0.18
    cej
    0.18
    Activations Density 0.066%

    No Known Activations