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. 20-LLAMASCOPE-RES-32K
    6. 27676
    Prev
    Next
    INDEX
    Explanations

    mentions of legal charges and convictions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arrest
    -0.19
    ictim
    -0.17
     arrest
    -0.17
     Mour
    -0.15
     Alleg
    -0.15
    thon
    -0.15
     allegations
    -0.14
    awks
    -0.14
    unta
    -0.14
     arrests
    -0.14
    POSITIVE LOGITS
     conviction
    0.33
     convictions
    0.30
    conv
    0.27
     sentence
    0.27
     Conv
    0.26
    Sentence
    0.25
    Conv
    0.24
     convicted
    0.24
     Sentence
    0.23
     sentenced
    0.23
    Activations Density 0.073%

    No Known Activations