© 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. 31-LLAMASCOPE-RES-32K
    11. 10569
    Prev
    Next
    INDEX
    Explanations

    phrases related to growth and development in professions

    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
    insi
    -0.12
    ICLE
    -0.12
    -simple
    -0.12
    #
    -0.12
     mutable
    -0.11
    ùng
    -0.11
    ãĥĨãĥ«
    -0.11
     Enumerator
    -0.11
    ')."
    -0.11
    enk
    -0.11
    POSITIVE LOGITS
     renowned
    0.52
     famous
    0.48
     renown
    0.47
     famed
    0.44
     leading
    0.43
     prestigious
    0.43
     prominent
    0.43
     esteemed
    0.42
     respected
    0.42
     eminent
    0.41
    Activations Density 0.848%

    No Known Activations