© 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. 23-LLAMASCOPE-RES-32K
    6. 31354
    Prev
    Next
    INDEX
    Explanations

    references to fandom and enthusiasts, particularly surrounding entertainment or sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chia
    -0.18
    ibri
    -0.16
    rians
    -0.15
    onta
    -0.15
    oop
    -0.14
    ÃŃrk
    -0.14
    ваннÑı
    -0.14
    .SDK
    -0.14
    tures
    -0.14
    ież
    -0.14
    POSITIVE LOGITS
    fare
    0.32
    atics
    0.32
    atical
    0.32
    atic
    0.24
    club
    0.21
    atically
    0.21
     club
    0.20
    stasy
    0.20
    atik
    0.19
    etic
    0.19
    Activations Density 0.008%

    No Known Activations