© 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. 30-LLAMASCOPE-RES-32K
    6. 17345
    Prev
    Next
    INDEX
    Explanations

    expressions and constructs used in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oji
    -0.18
     Gum
    -0.17
    hlen
    -0.15
    ardy
    -0.15
    ukt
    -0.14
    gio
    -0.14
    lien
    -0.14
    nev
    -0.14
    hive
    -0.14
    .normalized
    -0.14
    POSITIVE LOGITS
     Natural
    0.18
     natural
    0.17
    оÑĢдин
    0.15
     reverse
    0.15
     track
    0.15
     Bran
    0.15
    natural
    0.15
    append
    0.15
    	append
    0.14
    Į
    0.14
    Activations Density 0.026%

    No Known Activations