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. 4-LLAMASCOPE-RES-32K
    6. 2276
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to composition and writing structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abox
    -0.15
    infos
    -0.15
    swire
    -0.15
    icmp
    -0.14
    elfast
    -0.14
    req
    -0.14
    ãģ¿
    -0.14
     aç
    -0.14
    encion
    -0.14
    eatures
    -0.14
    POSITIVE LOGITS
    ÑĥÑĢÑĥ
    0.15
     Wr
    0.15
     Neville
    0.15
    ilde
    0.14
    alus
    0.14
     Charge
    0.14
    iju
    0.14
    ffen
    0.13
    665
    0.13
    urdu
    0.13
    Activations Density 0.309%

    No Known Activations