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. 10-LLAMASCOPE-RES-32K
    6. 9431
    Prev
    Next
    INDEX
    Explanations

    references to social issues and the implications of actions on society

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ersen
    -0.19
    readcr
    -0.18
    rych
    -0.16
    ÑĢоÑĩ
    -0.14
    ocks
    -0.14
    enario
    -0.14
    plr
    -0.14
    /inet
    -0.14
    zych
    -0.14
     addCriterion
    -0.13
    POSITIVE LOGITS
     indeed
    0.17
     ÙĪØ£ÙĨ
    0.15
    far
    0.14
     Batt
    0.14
    asil
    0.13
    oplast
    0.13
    ossa
    0.13
    arend
    0.13
    oop
    0.13
    лага
    0.12
    Activations Density 1.094%

    No Known Activations