© 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. 22-LLAMASCOPE-RES-32K
    11. 1568
    Prev
    Next
    INDEX
    Explanations

    phrases related to investment opportunities and financial analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     entail
    -0.16
    isan
    -0.15
    lish
    -0.15
     meant
    -0.15
    igung
    -0.14
    ÑĢаÑĤ
    -0.14
    arters
    -0.14
    usan
    -0.14
    ixin
    -0.13
    gens
    -0.13
    POSITIVE LOGITS
     closely
    0.36
     matches
    0.35
     match
    0.33
     MATCH
    0.29
     mirrors
    0.28
    match
    0.28
     mirror
    0.27
    -match
    0.27
    matches
    0.27
     reflect
    0.26
    Activations Density 0.360%

    No Known Activations