© 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. 9-LLAMASCOPE-RES-32K
    11. 26099
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the presence of "where" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ERCHANT
    -0.14
    lico
    -0.14
    matic
    -0.14
    whatever
    -0.14
    ants
    -0.14
    cri
    -0.14
    nj
    -0.13
    ноÑĩ
    -0.13
    them
    -0.13
    nya
    -0.13
    POSITIVE LOGITS
    upon
    0.23
    abouts
    0.20
    -ever
    0.15
    -нибÑĥдÑĮ
    0.15
     applicable
    0.15
    after
    0.15
    itzer
    0.14
    VER
    0.14
    /by
    0.14
    bij
    0.14
    Activations Density 0.076%

    No Known Activations