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. 3785
    Prev
    Next
    INDEX
    Explanations

    verbs and phrases related to facilitation, support, or action in various contexts

    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
    obel
    -0.17
     alt
    -0.15
    ulo
    -0.14
    inho
    -0.14
    undry
    -0.14
    xing
    -0.14
    abis
    -0.13
    .googleapis
    -0.13
    ndon
    -0.13
    olver
    -0.13
    POSITIVE LOGITS
    ugins
    0.18
    ικο
    0.18
    eland
    0.15
    ä¹ĭä¸Ģ
    0.15
    efs
    0.15
    Jvm
    0.15
    _UT
    0.15
    å¦Ĥä¸ĭ
    0.14
    getMock
    0.14
    [$_
    0.14
    Activations Density 0.189%

    No Known Activations