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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12-LLAMASCOPE-RES-32K
    6. 6041
    Prev
    Next
    INDEX
    Explanations

    phrases indicating cessation or discontinuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lucky
    -0.16
     Pron
    -0.15
    yy
    -0.15
     masih
    -0.15
     Still
    -0.14
    ãĥ¥
    -0.14
     still
    -0.14
    .opend
    -0.14
    ively
    -0.14
     fortunate
    -0.14
    POSITIVE LOGITS
    theless
    0.19
    epad
    0.16
    iegel
    0.16
    withstanding
    0.16
     anymore
    0.15
    нимаеÑĤ
    0.15
    hatt
    0.15
    βε
    0.14
    /uploads
    0.14
    _usec
    0.14
    Activations Density 0.023%

    No Known Activations