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. 19-LLAMASCOPE-RES-32K
    6. 25759
    Prev
    Next
    INDEX
    Explanations

    topics related to systemic injustice and the criminal justice system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ataire
    -0.17
    екÑĤи
    -0.15
     intrig
    -0.15
    лиз
    -0.14
    stab
    -0.14
     multiline
    -0.14
    véd
    -0.14
    indre
    -0.14
    ÅĻen
    -0.13
    ÐĿаÑģ
    -0.13
    POSITIVE LOGITS
    .sent
    0.18
     Sent
    0.17
    sent
    0.16
     reform
    0.16
     racial
    0.15
     militar
    0.15
     bail
    0.15
    alytics
    0.15
    Sent
    0.15
     sentences
    0.15
    Activations Density 0.067%

    No Known Activations