© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 3521
    Prev
    Next
    INDEX
    Explanations

    phrases indicating physical proximity and accessibility

    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
    bedo
    -0.14
    $sub
    -0.14
    ÏĦεÏģ
    -0.13
    ستگÛĮ
    -0.13
    ovo
    -0.13
    halt
    -0.13
    éné
    -0.13
     leve
    -0.13
    roker
    -0.13
    usra
    -0.13
    POSITIVE LOGITS
     sight
    0.55
     reach
    0.50
     range
    0.49
     view
    0.49
    view
    0.36
    range
    0.36
     vision
    0.35
     Sight
    0.35
     Range
    0.34
     site
    0.33
    Activations Density 0.078%

    No Known Activations