© 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. 25-LLAMASCOPE-RES-32K
    11. 23016
    Prev
    Next
    INDEX
    Explanations

    concepts related to distance and spatial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ektir
    -0.15
     Dawson
    -0.15
     Yates
    -0.14
    egrator
    -0.14
    iaux
    -0.14
    ota
    -0.13
     YYYY
    -0.13
     timespec
    -0.13
     Chocolate
    -0.13
    974
    -0.13
    POSITIVE LOGITS
     distance
    1.34
     Distance
    1.21
    distance
    1.17
     distances
    1.14
    Distance
    1.11
    -distance
    1.01
    _distance
    0.93
     distancia
    0.90
    .distance
    0.90
    è·Ŀ离
    0.89
    Activations Density 0.234%

    No Known Activations