© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-32K
    11. 3493
    Prev
    Next
    INDEX
    Explanations

    the word "out," particularly in contexts related to availability or accessibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ich
    -0.15
    ingly
    -0.15
    ruz
    -0.15
    è¡
    -0.14
    elter
    -0.14
    lef
    -0.14
    ét
    -0.14
    villa
    -0.14
     поÑģ
    -0.13
    utin
    -0.13
    POSITIVE LOGITS
     there
    0.27
     out
    0.21
    there
    0.20
     THERE
    0.20
    There
    0.17
     There
    0.17
     ÙĩÙĨاÙĥ
    0.17
     Out
    0.16
    uada
    0.16
     Ø¢ÙĨجا
    0.16
    Activations Density 0.011%

    No Known Activations