© 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. 14-LLAMASCOPE-RES-32K
    11. 12178
    Prev
    Next
    INDEX
    Explanations

    patterns of justification and excusing behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    racak
    -0.15
    (strtolower
    -0.15
    HN
    -0.14
    _HAND
    -0.14
    eck
    -0.14
     Stout
    -0.13
     Mundo
    -0.13
    ยม
    -0.13
    stva
    -0.13
    åİ
    -0.13
    POSITIVE LOGITS
     justification
    0.18
    оваÑĢи
    0.17
     justify
    0.16
    طاÙĤ
    0.15
    ÑĦи
    0.15
    orney
    0.14
    away
    0.14
     foreign
    0.14
     why
    0.14
    quals
    0.14
    Activations Density 0.195%

    No Known Activations