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. 7-LLAMASCOPE-RES-32K
    6. 11766
    Prev
    Next
    INDEX
    Explanations

    technical jargon and syntactical structures related to programming and web development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plat
    -0.16
    dej
    -0.15
     Got
    -0.15
    zym
    -0.15
    â̦I
    -0.14
    itlement
    -0.14
    ãĥķãĤ
    -0.14
    anson
    -0.14
    udes
    -0.14
    uz
    -0.14
    POSITIVE LOGITS
    NECT
    0.19
    588
    0.14
    metatable
    0.13
    ÙĪÛĮØ´
    0.13
    ÙĨØ´
    0.13
    -meta
    0.13
    amilia
    0.13
    286
    0.13
     ÙħعرÙģÛĮ
    0.13
    CompatActivity
    0.13
    Activations Density 1.411%

    No Known Activations