© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 18-LLAMASCOPE-RES-32K
    11. 25306
    Prev
    Next
    INDEX
    Explanations

    phrases indicating instructions or guidance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    swire
    -0.17
     Dod
    -0.15
    ÑģÑĸ
    -0.15
    @nate
    -0.14
    ildo
    -0.13
    ambil
    -0.13
     disgr
    -0.13
    Delayed
    -0.13
    uhn
    -0.13
    ác
    -0.13
    POSITIVE LOGITS
     pie
    0.16
    kaar
    0.15
    utsche
    0.15
     Taj
    0.14
     olma
    0.14
     league
    0.14
    VML
    0.14
    nick
    0.14
    pie
    0.14
    Ïĩο
    0.14
    Activations Density 0.000%

    No Known Activations