© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 1-LLAMASCOPE-RES-32K
    6. 14931
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers relating to programming or data structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¾
    -0.16
    åĨ
    -0.14
     Imp
    -0.14
    zap
    -0.14
    ]bool
    -0.14
    ousse
    -0.14
    ritz
    -0.14
     Yap
    -0.14
    aret
    -0.14
    ırak
    -0.13
    POSITIVE LOGITS
    rame
    0.16
    lsi
    0.15
    ä¿Ĺ
    0.15
    furt
    0.14
    iltr
    0.14
    еÑĢÑĮ
    0.14
    esda
    0.14
    dale
    0.14
    rowable
    0.13
    basket
    0.13
    Activations Density 0.078%

    No Known Activations