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. 14-LLAMASCOPE-RES-32K
    6. 12593
    Prev
    Next
    INDEX
    Explanations

    descriptions related to architectural features and structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ñıж
    -0.15
    otto
    -0.15
    orks
    -0.15
     Kendrick
    -0.15
    лав
    -0.15
    еÑı
    -0.14
    份
    -0.14
     Fork
    -0.14
    adies
    -0.14
    oyer
    -0.14
    POSITIVE LOGITS
     surface
    0.29
     surfaces
    0.26
     Surface
    0.24
    surface
    0.23
    Surface
    0.22
    Exposed
    0.19
    urface
    0.18
    _surface
    0.17
     face
    0.17
     facing
    0.17
    Activations Density 0.176%

    No Known Activations