© 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. 30-LLAMASCOPE-RES-32K
    11. 2887
    Prev
    Next
    INDEX
    Explanations

    references to mitigation and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yms
    -0.18
    athan
    -0.17
    ãĥĩãĤ£ãĤ¢
    -0.17
    edo
    -0.15
    ipur
    -0.15
    еннÑı
    -0.14
    edin
    -0.14
    ETA
    -0.14
    hetto
    -0.14
     Ryu
    -0.14
    POSITIVE LOGITS
    ochond
    0.34
    igation
    0.29
    ubishi
    0.26
    igated
    0.22
    IGATION
    0.22
    anni
    0.22
    ford
    0.22
    igate
    0.21
    osis
    0.21
    igator
    0.21
    Activations Density 0.010%

    No Known Activations