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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 27-LLAMASCOPE-RES-32K
    6. 10698
    Prev
    Next
    INDEX
    Explanations

    instances of the word "buck" and its variations, indicating a focus on financial topics or references to currency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /cop
    -0.16
    еÑģи
    -0.15
    ÑĨен
    -0.15
    seau
    -0.15
    cope
    -0.14
    kj
    -0.14
     fours
    -0.14
    ÙĴد
    -0.14
    ikes
    -0.14
    documents
    -0.14
    POSITIVE LOGITS
    ingham
    0.32
    eye
    0.29
    minster
    0.28
    aroo
    0.27
    eyes
    0.24
    nell
    0.22
    skin
    0.21
    ets
    0.20
    shot
    0.19
    aro
    0.19
    Activations Density 0.008%

    No Known Activations