© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 30-LLAMASCOPE-RES-32K
    6. 17378
    Prev
    Next
    INDEX
    Explanations

    instances of the word "kill" and its variations related to violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iland
    -0.18
    onto
    -0.15
    ulled
    -0.15
    /out
    -0.14
    iÃŁ
    -0.14
    /Framework
    -0.14
     Blur
    -0.14
    elect
    -0.14
    oha
    -0.14
    land
    -0.14
    POSITIVE LOGITS
     off
    0.23
    joy
    0.20
     spree
    0.20
    /disable
    0.20
    switch
    0.19
    æĪ
    0.19
    lier
    0.18
    deer
    0.18
    çİ°åľº
    0.17
    ibri
    0.17
    Activations Density 0.047%

    No Known Activations