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

    Neuronpedia

    Jacobian LensNEW
    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. 6-LLAMASCOPE-RES-32K
    11. 29902
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to data handling and event management

    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
    ury
    -0.18
    by
    -0.17
     CHILD
    -0.17
    enko
    -0.16
    uri
    -0.15
    b
    -0.15
    ic
    -0.15
    x
    -0.15
     sil
    -0.15
    m
    -0.14
    POSITIVE LOGITS
    .scalablytyped
    0.19
     Kür
    0.17
    spath
    0.16
    interop
    0.15
    _Il
    0.15
     Kurul
    0.14
    acional
    0.14
    bigint
    0.14
    LTR
    0.14
    /***/
    0.14
    Activations Density 1.471%

    No Known Activations