© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 22081
    Prev
    Next
    INDEX
    Explanations

    themes of deception and hidden truths

    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
     misc
    -0.15
    TON
    -0.14
    ton
    -0.14
    ueil
    -0.14
    >tag
    -0.14
    wealth
    -0.13
     fist
    -0.13
    onia
    -0.13
    @g
    -0.13
    uel
    -0.13
    POSITIVE LOGITS
    iegel
    0.14
    rim
    0.14
     doPost
    0.14
     Wolff
    0.14
     Fold
    0.14
     Sever
    0.14
     Rod
    0.14
    -ves
    0.14
    گراÙĨ
    0.14
     rodin
    0.14
    Activations Density 0.534%

    No Known Activations