© 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. 25-LLAMASCOPE-RES-32K
    11. 12264
    Prev
    Next
    INDEX
    Explanations

    phrases and information related to customer service inquiries and contact information

    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
    å±Ĭ
    -0.16
    виÑĩ
    -0.15
    ÃŃnh
    -0.14
    DEM
    -0.14
    ãĢ
    -0.14
    /latest
    -0.14
    onica
    -0.14
    aland
    -0.14
    atro
    -0.13
    .cv
    -0.13
    POSITIVE LOGITS
     toll
    0.43
     Toll
    0.36
    800
    0.34
    877
    0.28
    866
    0.28
    855
    0.28
    TTY
    0.26
    888
    0.26
    080
    0.23
    180
    0.23
    Activations Density 0.075%

    No Known Activations