© 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. 23-LLAMASCOPE-RES-32K
    11. 11887
    Prev
    Next
    INDEX
    Explanations

    elements related to technical specifications and visual representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ³ãĥĸ
    -0.14
     dirent
    -0.13
    edly
    -0.13
    Touches
    -0.13
    imates
    -0.12
     DecimalFormat
    -0.12
    uddenly
    -0.12
    _Impl
    -0.12
     manifestations
    -0.12
    jak
    -0.12
    POSITIVE LOGITS
     shown
    0.80
    shown
    0.65
     pictured
    0.60
    Shown
    0.58
    ictured
    0.54
    pictured
    0.54
     seen
    0.45
     below
    0.41
    seen
    0.41
     picture
    0.38
    Activations Density 0.488%

    No Known Activations