Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 17605
    Prev
    Next
    INDEX
    Explanations

    references to furniture and its attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    descriptions of furniture and home goods with their properties, materials, and quality features.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @danielepoterti
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odÃŃ
    -0.18
    วรร
    -0.16
    æł
    -0.16
    trys
    -0.16
    mq
    -0.15
    asin
    -0.15
    ERVER
    -0.15
    prd
    -0.15
    oney
    -0.15
    orners
    -0.14
    POSITIVE LOGITS
    518
    0.16
    087
    0.15
    åħĭæĸ¯
    0.15
     Martha
    0.15
    005
    0.14
    bourne
    0.14
    _gem
    0.14
    709
    0.14
    Compat
    0.14
    705
    0.14
    Activations Density 0.098%

    No Known Activations