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. 28-LLAMASCOPE-RES-32K
    6. 20753
    Prev
    Next
    INDEX
    Explanations

    key phrases and terms associated with significant events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogl
    -0.16
    luet
    -0.15
    urret
    -0.15
     salt
    -0.15
    лам
    -0.14
    æĹĹ
    -0.14
    BaseUrl
    -0.14
    вен
    -0.14
    .tap
    -0.14
    idal
    -0.14
    POSITIVE LOGITS
     binary
    0.16
    _binary
    0.16
    .interface
    0.15
    agh
    0.15
     Binary
    0.15
    -binary
    0.15
     gre
    0.14
     Patterson
    0.14
    iece
    0.14
     Victoria
    0.14
    Activations Density 0.018%

    No Known Activations