© 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. 3404
    Prev
    Next
    INDEX
    Explanations

    references to hyperlinks and media content

    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
    ','".$
    -0.11
    _Tis
    -0.10
     адже
    -0.09
     зокÑĢема
    -0.09
    _Statics
    -0.09
    $fdata
    -0.09
    ertino
    -0.09
    afort
    -0.08
     prvnÃŃm
    -0.08
    ½æķ°
    -0.08
    POSITIVE LOGITS
     =
    0.78
    =
    0.66
     =↵
    0.57
    =(
    0.49
    ="
    0.49
    .=
    0.48
    ='
    0.47
     ==
    0.47
    =\
    0.47
    =-
    0.47
    Activations Density 3.309%

    No Known Activations