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

    Neuronpedia

    APICircuit 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. 29-LLAMASCOPE-RES-32K
    6. 3290
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes, indicating a focus on web development or coding elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MainAxisAlignment
    -0.13
    autorelease
    -0.12
    mbH
    -0.12
     initWithTitle
    -0.12
    ãĥĥãĥĪ
    -0.12
    ãĥĥãĥĦ
    -0.12
    GW
    -0.12
    ụy
    -0.12
    ullan
    -0.12
    लत
    -0.11
    POSITIVE LOGITS
    -N
    0.80
    ÂłN
    0.73
    _N
    0.69
    -n
    0.66
    .N
    0.59
    N
    0.54
    	N
    0.54
    ,N
    0.53
    /N
    0.52
    (N
    0.52
    Activations Density 0.750%

    No Known Activations