© 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. 17721
    Prev
    Next
    INDEX
    Explanations

    historical references and specific names

    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
    ìn
    -0.15
    illos
    -0.14
    -rated
    -0.13
    ød
    -0.13
    ignon
    -0.13
    leton
    -0.13
     ÑĢÑĥками
    -0.13
     Leer
    -0.12
     éĿĴ
    -0.12
    ообÑĢаз
    -0.12
    POSITIVE LOGITS
     name
    0.36
     rename
    0.33
     renaming
    0.31
     names
    0.29
    rename
    0.29
    åIJį称
    0.28
     Rename
    0.28
     Name
    0.28
    .name
    0.28
     change
    0.27
    Activations Density 0.180%

    No Known Activations