Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 24-LLAMASCOPE-RES-32K
    6. 20729
    Prev
    Next
    INDEX
    Explanations

    issues related to access to basic human needs and services

    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
     gol
    -0.15
    znam
    -0.14
    ä¹Ĺ
    -0.14
    riet
    -0.14
    üf
    -0.14
     captivity
    -0.13
     smoker
    -0.13
    etik
    -0.13
    slack
    -0.13
    ancia
    -0.13
    POSITIVE LOGITS
     basic
    0.39
    basic
    0.35
     housing
    0.33
    -basic
    0.31
     Basic
    0.31
     basics
    0.30
     healthcare
    0.29
    Basic
    0.29
     BASIC
    0.28
     access
    0.28
    Activations Density 0.244%

    No Known Activations