© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 29-LLAMASCOPE-RES-32K
    6. 11862
    Prev
    Next
    INDEX
    Explanations

    tools and methods for assessment and evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     elucid
    -0.15
    ĻĤ
    -0.15
    isay
    -0.15
     elabor
    -0.14
    ÏĢοιη
    -0.14
    mention
    -0.13
    ixmap
    -0.13
    ards
    -0.13
    kö
    -0.13
    notated
    -0.13
    POSITIVE LOGITS
     determine
    0.49
     figure
    0.45
     gauge
    0.43
     determines
    0.41
     determining
    0.40
     see
    0.38
     Determine
    0.36
     determined
    0.36
     judge
    0.36
     determin
    0.35
    Activations Density 0.364%

    No Known Activations