© 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. 16-LLAMASCOPE-RES-32K
    11. 8043
    Prev
    Next
    INDEX
    Explanations

    conditional statements and contrasts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ogan
    -0.18
    chen
    -0.16
    ys
    -0.14
     subjective
    -0.13
    hek
    -0.13
    à¤ĩन
    -0.13
    imest
    -0.13
    ès
    -0.13
    ảng
    -0.13
    inks
    -0.13
    POSITIVE LOGITS
     only
    0.28
     ONLY
    0.22
    only
    0.21
    Only
    0.20
    .only
    0.20
     seulement
    0.20
     ÑĤолÑĮко
    0.19
     Only
    0.18
    _only
    0.17
    åıª
    0.17
    Activations Density 0.186%

    No Known Activations