© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 14-LLAMASCOPE-RES-32K
    11. 22411
    Prev
    Next
    INDEX
    Explanations

    syntactic or structural elements in code snippets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sj
    -0.19
    ses
    -0.16
    ych
    -0.16
    raj
    -0.16
    oki
    -0.16
    side
    -0.15
    ãĤº
    -0.15
    ucci
    -0.14
    spo
    -0.14
    ský
    -0.14
    POSITIVE LOGITS
    iode
    0.17
    eel
    0.17
    al
    0.16
    apus
    0.15
    ibt
    0.15
    alet
    0.14
    edia
    0.14
    htub
    0.14
    ctrine
    0.14
    elts
    0.14
    Activations Density 0.305%

    No Known Activations