© 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. 18062
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "being" in various contexts

    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
    lse
    -0.17
    kü
    -0.15
     Beginning
    -0.15
     differing
    -0.15
    ácil
    -0.15
    ocator
    -0.14
    ulumi
    -0.14
     beginning
    -0.14
     remaining
    -0.14
    woke
    -0.14
    POSITIVE LOGITS
     able
    0.35
     unable
    0.27
    ness
    0.26
     part
    0.23
     asked
    0.21
     Able
    0.20
     apart
    0.20
     told
    0.20
     offered
    0.20
     around
    0.20
    Activations Density 0.060%

    No Known Activations