© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-32K
    11. 17606
    Prev
    Next
    INDEX
    Explanations

    assertions about policy success and failure scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gii
    -0.17
    anja
    -0.14
    rets
    -0.14
     Mist
    -0.14
     ups
    -0.14
    æľĽ
    -0.14
     Reform
    -0.13
    ÑĢоÑģÑĤо
    -0.13
    enth
    -0.13
    .retrieve
    -0.13
    POSITIVE LOGITS
    ocker
    0.15
    ساس
    0.14
    igung
    0.14
    JK
    0.14
    ewis
    0.13
    _TRA
    0.13
     Baghd
    0.13
    è«
    0.13
    0.13
     Handy
    0.13
    Activations Density 0.038%

    No Known Activations