© 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. 12-LLAMASCOPE-RES-32K
    11. 24644
    Prev
    Next
    INDEX
    Explanations

    expressions of physical affection and emotional interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cry
    -0.16
    ứng
    -0.14
    Ø®ÙĬ
    -0.14
    ens
    -0.14
    /head
    -0.14
    cry
    -0.13
    ips
    -0.13
    leaf
    -0.13
    istics
    -0.13
    itas
    -0.13
    POSITIVE LOGITS
    ULO
    0.18
    kees
    0.17
    -UA
    0.16
    ãĥĥãĥĦ
    0.15
    richt
    0.14
    ãĤ¡
    0.14
     gql
    0.14
    FX
    0.14
    .dtp
    0.14
    ichick
    0.14
    Activations Density 0.205%

    No Known Activations