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. 1-LLAMASCOPE-RES-32K
    6. 23148
    Prev
    Next
    INDEX
    Explanations

    phrases with the conjunction "and" to identify complex relationships or connections between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interest
    -0.14
     hit
    -0.14
     (
    -0.14
    ucch
    -0.13
    OW
    -0.13
     material
    -0.13
     sens
    -0.13
     tend
    -0.13
    zed
    -0.13
     artificial
    -0.13
    POSITIVE LOGITS
    polator
    0.17
    ContentLoaded
    0.16
    iare
    0.15
    alama
    0.15
    @nate
    0.15
    baugh
    0.15
    oulos
    0.15
    /*č↵
    0.15
    ân
    0.14
    .CustomButton
    0.14
    Activations Density 0.658%

    No Known Activations