© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-32K
    11. 22037
    Prev
    Next
    INDEX
    Explanations

    references to related content and stories

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÑĢÑĥн
    -0.16
     PMID
    -0.13
     Butter
    -0.12
    878
    -0.12
    .failure
    -0.12
    .ease
    -0.12
    _syntax
    -0.12
    udd
    -0.12
    ô
    -0.12
     é¹
    -0.12
    POSITIVE LOGITS
    :↵
    0.25
    ï¼ļ↵
    0.19
    :↵↵↵
    0.18
    :↵↵
    0.18
     :↵
    0.18
    :č↵
    0.17
     related
    0.17
    ):↵
    0.17
    ':↵
    0.17
    ():↵
    0.16
    Activations Density 0.046%

    No Known Activations