© 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. 7768
    Prev
    Next
    INDEX
    Explanations

    instances of the word "same" 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 @ 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
    á»Ļng
    -0.16
    rico
    -0.16
     ðŁĺī↵↵
    -0.15
    HING
    -0.15
    ento
    -0.15
    rus
    -0.15
    atu
    -0.15
    addtogroup
    -0.14
    лив
    -0.14
    rito
    -0.14
    POSITIVE LOGITS
     token
    0.21
    941
    0.18
    384
    0.17
     moment
    0.16
     time
    0.16
    -token
    0.16
    359
    0.15
     tokens
    0.15
    ="__
    0.15
     breath
    0.15
    Activations Density 0.014%

    No Known Activations