© 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. 28-LLAMASCOPE-RES-32K
    11. 17415
    Prev
    Next
    INDEX
    Explanations

    verbs and actions related to betrayal, acknowledgment, and branding efforts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    IZED
    -0.15
    uzzer
    -0.15
    ALLY
    -0.14
    lify
    -0.14
    osate
    -0.14
    isable
    -0.14
    olest
    -0.13
    uida
    -0.13
    ucer
    -0.13
    ARGIN
    -0.13
    POSITIVE LOGITS
    ing
    1.73
    ING
    1.02
    ingt
    0.68
    инг
    0.56
    ingen
    0.53
    ë§ģ
    0.49
    ings
    0.48
    ãĥ³ãĤ°
    0.48
    ting
    0.48
    ingo
    0.46
    Activations Density 0.456%

    No Known Activations