© 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. 21452
    Prev
    Next
    INDEX
    Explanations

    performance metrics and statistics related to baseball players and games

    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
    =Value
    -0.14
    ean
    -0.14
    alse
    -0.13
    ROKE
    -0.13
    ymph
    -0.13
    æŃ
    -0.13
    Tail
    -0.13
    ugs
    -0.13
    amba
    -0.13
    ALSE
    -0.13
    POSITIVE LOGITS
    ALLOW
    0.20
     retired
    0.18
     retiring
    0.18
    limits
    0.18
    kees
    0.18
    .EXIT
    0.18
     scattered
    0.18
     allow
    0.18
     ALLOW
    0.17
     allowed
    0.17
    Activations Density 0.021%

    No Known Activations