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. 20-LLAMASCOPE-RES-32K
    6. 26067
    Prev
    Next
    INDEX
    Explanations

    instances of home-related ideas and suggestions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĪев
    -0.16
    imon
    -0.16
    .scalablytyped
    -0.15
    imli
    -0.14
    adera
    -0.13
     Domino
    -0.13
    .Provider
    -0.13
    iera
    -0.13
    _mono
    -0.13
    лÑĸн
    -0.13
    POSITIVE LOGITS
    obi
    0.15
    สาร
    0.15
    olla
    0.15
    ilst
    0.15
    unal
    0.15
    udos
    0.14
    ATS
    0.14
    é³´
    0.14
    ej
    0.14
    795
    0.14
    Activations Density 0.002%

    No Known Activations