© 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. 10318
    Prev
    Next
    INDEX
    Explanations

    names of athletes and references to sporting events

    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
     pis
    -0.16
    enge
    -0.16
    еÑĢп
    -0.15
    itere
    -0.15
    ê¸ī
    -0.15
    ipay
    -0.15
     виÑĤ
    -0.14
    gateway
    -0.14
    odate
    -0.14
     Sutton
    -0.14
    POSITIVE LOGITS
     Nov
    0.20
     Murray
    0.19
     Gael
    0.18
     Fritz
    0.17
     Matte
    0.17
    Nov
    0.17
     Dominic
    0.17
     Ts
    0.17
     Marin
    0.17
     clay
    0.17
    Activations Density 0.004%

    No Known Activations