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. 4-LLAMASCOPE-RES-32K
    6. 23427
    Prev
    Next
    INDEX
    Explanations

    instances of the word "surprise" and similar phrases expressing unexpectedness or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    les
    -0.17
    hx
    -0.15
    scribe
    -0.14
    edy
    -0.14
    byt
    -0.14
    Ñĩил
    -0.14
    ét
    -0.14
    ecimal
    -0.14
     Rig
    -0.14
    ãĢ
    -0.14
    POSITIVE LOGITS
    777
    0.17
    ãĥĥ
    0.17
    .ibatis
    0.16
    vail
    0.14
     آذ
    0.14
    COPE
    0.14
     Alan
    0.14
    ÑĢаÑīениÑı
    0.13
    adier
    0.13
    790
    0.13
    Activations Density 0.472%

    No Known Activations