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. 12-LLAMASCOPE-RES-32K
    6. 14115
    Prev
    Next
    INDEX
    Explanations

    instances of template-related programming constructs

    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
    raj
    -0.17
    icans
    -0.15
    sWith
    -0.15
    ried
    -0.14
    coat
    -0.14
     Savage
    -0.14
     Atmospheric
    -0.14
     поÑĤол
    -0.13
     mee
    -0.13
     Braun
    -0.13
    POSITIVE LOGITS
    Ctrls
    0.17
    ÃŃsto
    0.16
     Fallen
    0.15
    огод
    0.15
    ç¥Ń
    0.15
    979
    0.14
    yntax
    0.14
    629
    0.14
    etyl
    0.14
     pron
    0.14
    Activations Density 0.001%

    No Known Activations