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. 30-LLAMASCOPE-RES-32K
    6. 4619
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations and addresses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lorem
    -0.16
    ÑŁ
    -0.15
    ÏĢλ
    -0.15
    lou
    -0.14
     listItem
    -0.14
     actionTypes
    -0.14
    locker
    -0.13
    (æ°´
    -0.13
    ilon
    -0.13
    _mE
    -0.13
    POSITIVE LOGITS
     L
    1.40
    L
    0.92
    ÂłL
    0.83
    =L
    0.78
    $L
    0.74
    *L
    0.72
    :L
    0.69
    .L
    0.69
     ÐĽ
    0.67
    	L
    0.66
    Activations Density 0.859%

    No Known Activations