© 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. 18-LLAMASCOPE-RES-32K
    11. 14776
    Prev
    Next
    INDEX
    Explanations

    relationships and expressions of love or affection

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    687
    -0.15
     Vill
    -0.13
    alus
    -0.13
    ÏĮν
    -0.13
    omb
    -0.13
    adesh
    -0.13
    Âłje
    -0.13
    AX
    -0.13
     ú
    -0.13
    afi
    -0.13
    POSITIVE LOGITS
     recip
    0.72
     reciprocal
    0.57
     recipro
    0.52
     mutual
    0.45
     retali
    0.40
     retal
    0.40
     reply
    0.38
     Mutual
    0.36
     retaliation
    0.36
     replies
    0.34
    Activations Density 0.330%

    No Known Activations