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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 30-LLAMASCOPE-RES-32K
    11. 15226
    Prev
    Next
    INDEX
    Explanations

    phrases that express uncertainty or difficulty in achieving goals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    stown
    -0.21
     conducted
    -0.17
     Conduct
    -0.17
     Duis
    -0.16
    nze
    -0.15
    使
    -0.15
    à¹Ĥà¸ģ
    -0.15
    listening
    -0.15
     makes
    -0.15
    do
    -0.15
    POSITIVE LOGITS
    sink
    0.16
     sink
    0.16
     conquer
    0.15
    erial
    0.15
     readily
    0.14
     behold
    0.14
    βι
    0.14
     meiden
    0.14
     ÙĤب
    0.14
     diminished
    0.14
    Activations Density 0.152%

    No Known Activations