© 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. 20-LLAMASCOPE-RES-32K
    11. 13592
    Prev
    Next
    INDEX
    Explanations

    references to formatting and annotations in written content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    istrat
    -0.18
    ieg
    -0.16
    adow
    -0.16
    asl
    -0.15
    paragraph
    -0.15
    Canonical
    -0.14
    ubl
    -0.14
    ανά
    -0.14
    urt
    -0.14
    haf
    -0.14
    POSITIVE LOGITS
     trailing
    0.22
     suffix
    0.21
     extra
    0.18
     suff
    0.18
     thêm
    0.18
     ÑģÑĥ
    0.18
     added
    0.18
     postfix
    0.16
     leading
    0.16
     добав
    0.16
    Activations Density 0.173%

    No Known Activations