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. 27-LLAMASCOPE-RES-32K
    6. 1802
    Prev
    Next
    INDEX
    Explanations

    expressions of well-wishing or encouragement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ίκ
    -0.15
    è®
    -0.15
    oppers
    -0.15
    _funcs
    -0.14
    елиÑĩ
    -0.14
    lap
    -0.14
    \Lib
    -0.14
    urdu
    -0.14
    .motion
    -0.14
    lien
    -0.14
    POSITIVE LOGITS
     luck
    0.31
     success
    0.27
     best
    0.24
     bonne
    0.23
     continued
    0.23
     nothing
    0.23
     good
    0.22
     Continued
    0.21
     well
    0.21
     health
    0.20
    Activations Density 0.017%

    No Known Activations