© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 18074
    Prev
    Next
    INDEX
    Explanations

    conditional statements and phrases that initiate an inquiry or suggestion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    draul
    -0.15
    bable
    -0.14
    alloca
    -0.14
    "label
    -0.14
    _Tool
    -0.13
    uzzy
    -0.13
    sembler
    -0.13
    onymous
    -0.13
    LEncoder
    -0.13
    COOKIE
    -0.13
    POSITIVE LOGITS
     Quotes
    0.17
    ↵↵
    0.15
     Poh
    0.15
    :↵↵
    0.14
     embodiments
    0.14
    =int
    0.14
    (/^
    0.14
    amo
    0.13
    ()↵↵
    0.13
     /^
    0.13
    Activations Density 0.544%

    No Known Activations