© 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. 5-LLAMASCOPE-RES-32K
    11. 15617
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their association with narrative structure or dialogue

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elines
    -0.15
     Lal
    -0.15
    avel
    -0.15
    catid
    -0.14
    rowsable
    -0.14
    mamak
    -0.14
    apel
    -0.14
     SAN
    -0.14
    /we
    -0.14
    ses
    -0.14
    POSITIVE LOGITS
    é¡¿
    0.14
     dw
    0.14
    anut
    0.14
    boom
    0.14
    ç»ıçIJĨ
    0.14
    Forge
    0.14
    inst
    0.14
    íĺ¼
    0.14
    asc
    0.13
     absol
    0.13
    Activations Density 0.251%

    No Known Activations