© 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. 8196
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to organizational structure and attributes

    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
    αÏģ
    -0.14
    ÏĦÏģι
    -0.14
    окÑģи
    -0.14
    ERA
    -0.14
    ãĤ¿ãĥ¼
    -0.13
    jos
    -0.13
    ora
    -0.13
    quals
    -0.13
    erdings
    -0.13
    ifs
    -0.13
    POSITIVE LOGITS
    iscard
    0.18
    .ht
    0.15
    almart
    0.14
    ombat
    0.14
    hread
    0.14
    UTURE
    0.14
    amarin
    0.14
    uild
    0.14
    fld
    0.14
    ¾
    0.13
    Activations Density 0.406%

    No Known Activations