© 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. 31-LLAMASCOPE-RES-32K
    6. 5992
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "do" and its variations in different grammatical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urette
    -0.16
    avia
    -0.14
    åł¡
    -0.13
    /App
    -0.13
    urge
    -0.13
    ationale
    -0.13
     dün
    -0.13
    رÙĬÙĤ
    -0.13
    оÑı
    -0.13
    hek
    -0.13
    POSITIVE LOGITS
    le
    0.32
    ze
    0.30
     something
    0.27
    cket
    0.26
     things
    0.26
     justice
    0.25
    ff
    0.25
    ctest
    0.23
     whatever
    0.23
     away
    0.23
    Activations Density 0.127%

    No Known Activations