© 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. 10-LLAMASCOPE-RES-32K
    11. 23723
    Prev
    Next
    INDEX
    Explanations

    instances of nested parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    674
    -0.15
    askell
    -0.14
    mart
    -0.14
    ERM
    -0.14
     sketch
    -0.13
    347
    -0.13
    andex
    -0.13
     mold
    -0.13
    ensed
    -0.13
    rouw
    -0.13
    POSITIVE LOGITS
    álo
    0.17
    chet
    0.15
    atrix
    0.15
    _tF
    0.14
    eness
    0.14
     EXTRA
    0.14
     Longer
    0.14
    ailles
    0.14
    razier
    0.13
    oneksi
    0.13
    Activations Density 0.007%

    No Known Activations