© 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. 7-LLAMASCOPE-RES-32K
    11. 8518
    Prev
    Next
    INDEX
    Explanations

    phrases regarding forward-looking statements and related risks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plode
    -0.15
    poons
    -0.15
    reator
    -0.14
    presso
    -0.14
    857
    -0.14
    ilenames
    -0.13
     exce
    -0.13
    æ¶ī
    -0.13
    wait
    -0.13
    pu
    -0.13
    POSITIVE LOGITS
    ç´
    0.14
    achen
    0.14
     analogue
    0.14
     anale
    0.13
     fitte
    0.13
     Fowler
    0.13
    jal
    0.13
    ilder
    0.13
    家æĹı
    0.13
    _ENABLED
    0.12
    Activations Density 0.066%

    No Known Activations