© 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 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. 25-LLAMASCOPE-RES-32K
    11. 21202
    Prev
    Next
    INDEX
    Explanations

    phrases relating to perceptions of reality and how people perceive their situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adla
    -0.16
    ãĤ¤ãĥ¤
    -0.15
    none
    -0.15
    ewan
    -0.14
    WND
    -0.14
    whereIn
    -0.14
    rowse
    -0.14
    -none
    -0.14
    vox
    -0.14
    bject
    -0.13
    POSITIVE LOGITS
     thus
    0.46
     this
    0.40
     asÃŃ
    0.39
    thus
    0.38
    è¿Ļæł·
    0.35
     ainsi
    0.35
     così
    0.34
    this
    0.33
    éĤ£æł·
    0.32
    Thus
    0.32
    Activations Density 0.307%

    No Known Activations