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. 26125
    Prev
    Next
    INDEX
    Explanations

    references to the brand or products associated with "Milio's."

    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
    eking
    -0.16
    icts
    -0.16
    all
    -0.15
    brick
    -0.15
     Peek
    -0.14
    TECT
    -0.14
    istics
    -0.14
    ment
    -0.14
    callable
    -0.13
    nelly
    -0.13
    POSITIVE LOGITS
    aukee
    0.32
    waukee
    0.24
    shake
    0.21
    vekili
    0.20
     Mil
    0.19
    uncios
    0.18
    imeter
    0.17
    isecond
    0.17
    sap
    0.16
    maid
    0.16
    Activations Density 0.029%

    No Known Activations