© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 20-LLAMASCOPE-RES-32K
    11. 22754
    Prev
    Next
    INDEX
    Explanations

    definitions and criteria related to success and leadership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asan
    -0.15
    utting
    -0.15
     Rational
    -0.14
     progn
    -0.14
    abit
    -0.14
     rational
    -0.14
    .tpl
    -0.14
     prognosis
    -0.14
     Nombre
    -0.13
    ande
    -0.13
    POSITIVE LOGITS
     definition
    0.82
     definitions
    0.73
     Definition
    0.71
    definition
    0.69
    -definition
    0.66
    Definition
    0.66
     Definitions
    0.61
    definitions
    0.60
    Definitions
    0.57
    _definition
    0.53
    Activations Density 0.337%

    No Known Activations