Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 31-LLAMASCOPE-RES-32K
    6. 31183
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or addresses, particularly involving "Dund"

    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
    ÑĤÑĢ
    -0.18
    ξη
    -0.17
    itors
    -0.16
    uraa
    -0.15
    abaj
    -0.15
    تÙħ
    -0.14
    LETTE
    -0.14
    SEL
    -0.14
    BERS
    -0.14
    utos
    -0.14
    POSITIVE LOGITS
    ee
    0.41
    onald
    0.36
    alk
    0.30
    rum
    0.28
    ees
    0.24
    een
    0.22
    eee
    0.22
    onian
    0.21
    ead
    0.21
    onn
    0.21
    Activations Density 0.005%

    No Known Activations