© 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. 26-LLAMASCOPE-RES-32K
    6. 10422
    Prev
    Next
    INDEX
    Explanations

    references to legal matters and status changes related to individuals and groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.26.hook_resid_post
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kee
    -0.15
    ·¨
    -0.13
     terk
    -0.13
    otr
    -0.13
    ¤í
    -0.13
    COPE
    -0.13
     disclosing
    -0.13
     cuffs
    -0.13
    ulp
    -0.13
    ãģ«è¦ĭ
    -0.13
    POSITIVE LOGITS
     official
    0.69
     officially
    0.62
    official
    0.59
     oficial
    0.58
     Official
    0.57
     formal
    0.55
    Official
    0.54
     оÑĦиÑĨи
    0.49
    æŃ£å¼ı
    0.48
     recognition
    0.46
    Activations Density 0.401%

    No Known Activations