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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 20-LLAMASCOPE-RES-32K
    6. 23862
    Prev
    Next
    INDEX
    Explanations

    calls to action related to signing up or subscribing

    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
    nila
    -0.17
    arde
    -0.16
    ickers
    -0.15
    MAND
    -0.15
    icket
    -0.15
    MITTED
    -0.14
    assa
    -0.14
    acin
    -0.14
    metis
    -0.14
    ickets
    -0.14
    POSITIVE LOGITS
     sign
    0.29
    ificantly
    0.26
    .sign
    0.26
    /sign
    0.26
    sign
    0.24
    atures
    0.24
    post
    0.23
     Sign
    0.22
    ificance
    0.22
    (sign
    0.22
    Activations Density 0.011%

    No Known Activations