© 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. 23-LLAMASCOPE-RES-32K
    11. 15421
    Prev
    Next
    INDEX
    Explanations

    references to IP addresses 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 @ 23-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     jadx
    -0.18
    adesh
    -0.15
    lk
    -0.15
    kle
    -0.15
    aru
    -0.15
    ë°ľ
    -0.15
    LEGRO
    -0.14
     hủy
    -0.14
    æ³ķ人
    -0.14
    ueil
    -0.14
    POSITIVE LOGITS
    sec
    0.24
    ython
    0.21
     address
    0.19
    Tables
    0.17
    iscing
    0.17
    secs
    0.17
    /ip
    0.17
    nut
    0.16
    ê¶ģ
    0.16
     rights
    0.16
    Activations Density 0.008%

    No Known Activations