© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 12-LLAMASCOPE-RES-32K
    11. 31795
    Prev
    Next
    INDEX
    Explanations

    code-related constructs, especially function calls and exit statuses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahat
    -0.15
    ahas
    -0.14
    à¸Ħรà¸ļ
    -0.14
    ya
    -0.14
    ëĭĿ
    -0.14
    HR
    -0.14
    rá
    -0.14
    <small
    -0.13
    éĢĨ
    -0.13
    indle
    -0.13
    POSITIVE LOGITS
    707
    0.16
    quat
    0.15
    edException
    0.15
    anova
    0.15
    illac
    0.15
    ëĿ½
    0.15
    iver
    0.14
    cla
    0.14
     goto
    0.14
    .Exists
    0.14
    Activations Density 0.035%

    No Known Activations