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. 7-LLAMASCOPE-RES-32K
    6. 17665
    Prev
    Next
    INDEX
    Explanations

    phrases or contexts that indicate expectation or conditional scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dued
    -0.15
    zek
    -0.15
    bert
    -0.15
    aub
    -0.14
    mars
    -0.14
    psilon
    -0.14
    yntax
    -0.14
     ----------------------------------------------------------------------------↵
    -0.13
    uel
    -0.13
    istor
    -0.13
    POSITIVE LOGITS
     to
    0.16
     them
    0.15
     us
    0.14
    rat
    0.14
    eteor
    0.13
     CDC
    0.13
     Dispatch
    0.13
    nets
    0.13
     Pointer
    0.13
    ance
    0.13
    Activations Density 0.187%

    No Known Activations