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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 23-LLAMASCOPE-RES-32K
    6. 11957
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hamm
    -0.13
    doch
    -0.12
    cion
    -0.12
    ÑĥÑĩа
    -0.12
     PyTuple
    -0.12
    ÃĹ↵↵
    -0.12
    Fonts
    -0.12
    ypse
    -0.12
    zman
    -0.12
    formance
    -0.12
    POSITIVE LOGITS
     L
    0.40
    $L
    0.36
     ल
    0.35
    ÂłL
    0.35
    _l
    0.33
     ÙĦ
    0.33
     ÐĽ
    0.33
     l
    0.33
     л
    0.32
    .L
    0.32
    Activations Density 0.773%

    No Known Activations