© 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. 17-LLAMASCOPE-RES-32K
    11. 5625
    Prev
    Next
    INDEX
    Explanations

    terms that convey strong emotions or preferences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acco
    -0.13
    \Abstract
    -0.13
    ancia
    -0.13
    polator
    -0.13
    ZN
    -0.13
    باÙĨ
    -0.13
    steller
    -0.13
    noho
    -0.13
    CEEDED
    -0.13
    conduct
    -0.12
    POSITIVE LOGITS
    /config
    0.14
    388
    0.14
    uiten
    0.13
    uda
    0.13
    mie
    0.13
    uil
    0.13
    ulla
    0.13
    bsites
    0.13
    428
    0.12
    ubby
    0.12
    Activations Density 0.031%

    No Known Activations