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. 28252
    Prev
    Next
    INDEX
    Explanations

    mentions of legal briefs and court cases related to gun rights

    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
    -basket
    -0.20
     tribunal
    -0.16
    調
    -0.16
    jur
    -0.16
    tring
    -0.16
    anki
    -0.15
     judge
    -0.15
    avax
    -0.15
     createContext
    -0.15
     jurors
    -0.15
    POSITIVE LOGITS
     argument
    0.28
     arguments
    0.28
     Arguments
    0.27
     Argument
    0.26
    Argument
    0.26
    icus
    0.26
     argue
    0.25
     argued
    0.25
     Arg
    0.24
     arguing
    0.24
    Activations Density 0.167%

    No Known Activations