© 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. 24-LLAMASCOPE-RES-32K
    11. 20890
    Prev
    Next
    INDEX
    Explanations

    descriptions related to superficiality and cliché in character representation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResponseBody
    -0.16
    ephir
    -0.15
    atham
    -0.15
     vidéos
    -0.15
    umo
    -0.14
     bordel
    -0.14
    avax
    -0.14
    ****************************
    -0.14
    ikh
    -0.14
    638
    -0.14
    POSITIVE LOGITS
     hack
    0.26
     kits
    0.25
     artificial
    0.24
     syrup
    0.24
     sac
    0.23
     tack
    0.23
    hack
    0.22
     chees
    0.22
     corn
    0.22
    kits
    0.21
    Activations Density 0.498%

    No Known Activations