© 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. 19-LLAMASCOPE-RES-32K
    11. 26246
    Prev
    Next
    INDEX
    Explanations

    instances of claims or statements related to societal issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÌĨ
    -0.16
    elif
    -0.15
    (strtolower
    -0.14
     espec
    -0.14
    ãĥ©ãĥĥãĤ¯
    -0.14
    ÙĦÛĮس
    -0.13
    ADM
    -0.13
    uden
    -0.13
    ç¨ĭ度
    -0.13
    eps
    -0.12
    POSITIVE LOGITS
     means
    0.81
     Means
    0.72
    means
    0.68
    Means
    0.65
     meaning
    0.63
    meaning
    0.59
     mean
    0.55
    æĦıåij³
    0.53
    Mean
    0.52
     Meaning
    0.52
    Activations Density 0.285%

    No Known Activations