© 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. 6-LLAMASCOPE-RES-32K
    11. 28501
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical subsets and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stal
    -0.21
    ANCELED
    -0.15
    lob
    -0.15
     Compound
    -0.15
    haus
    -0.15
    ulur
    -0.14
    lei
    -0.14
    orde
    -0.14
    ãĤīãģĹ
    -0.14
    fold
    -0.14
    POSITIVE LOGITS
    tero
    0.16
    OfFile
    0.16
    tery
    0.16
    emax
    0.16
    ters
    0.15
    RIPT
    0.15
    ermann
    0.15
    _vert
    0.14
    ption
    0.14
    amax
    0.14
    Activations Density 0.031%

    No Known Activations