© 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. 31-LLAMASCOPE-RES-32K
    6. 11198
    Prev
    Next
    INDEX
    Explanations

    PHP code snippets and functions related to data retrieval and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ael
    -0.15
    /interfaces
    -0.15
     اÙģØª
    -0.14
     Leopard
    -0.14
    Pacific
    -0.14
     Lexus
    -0.14
    orch
    -0.14
     Sakura
    -0.14
    orf
    -0.14
    atsby
    -0.14
    POSITIVE LOGITS
    ($_
    0.48
     $_
    0.47
    $_
    0.45
     ($_
    0.45
    [$_
    0.40
    =$_
    0.40
    ,$_
    0.39
    )$_
    0.37
    '=>$_
    0.35
     @$_
    0.35
    Activations Density 0.014%

    No Known Activations