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

    Neuronpedia

    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. 18678
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and demographic data

    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
     Tür
    -0.15
    oload
    -0.14
    tones
    -0.14
    íĺľ
    -0.14
     Ãľl
    -0.14
    ÑĢид
    -0.14
    isy
    -0.14
     ÙĦغ
    -0.14
    -lfs
    -0.14
     Province
    -0.13
    POSITIVE LOGITS
     Incorporated
    0.21
     GN
    0.21
    æ³ķ人
    0.19
     incorporated
    0.19
    GN
    0.19
    NECT
    0.18
     ancest
    0.18
     US
    0.17
     Ghost
    0.17
    lies
    0.16
    Activations Density 0.034%

    No Known Activations