Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 11-LLAMASCOPE-RES-32K
    6. 7304
    Prev
    Next
    INDEX
    Explanations

    important components and considerations in home improvement and brewing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antan
    -0.15
    779
    -0.15
    uga
    -0.15
    Äģn
    -0.15
    ROP
    -0.15
    434
    -0.13
    sob
    -0.13
    -regexp
    -0.13
    527
    -0.13
    /******/
    -0.13
    POSITIVE LOGITS
    uche
    0.15
    adlo
    0.15
    ugen
    0.15
    ç·Ĵ
    0.14
    ãĤ¤ãĤº
    0.14
    lection
    0.14
    /MPL
    0.14
    iro
    0.14
     importance
    0.13
    еж
    0.13
    Activations Density 0.283%

    No Known Activations