© 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. 16-LLAMASCOPE-RES-32K
    11. 18152
    Prev
    Next
    INDEX
    Explanations

    negations and phrases indicating uncertainty or lack of clarity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idir
    -0.15
    asive
    -0.15
     Kro
    -0.15
    PÅĻed
    -0.14
    etti
    -0.14
    ylon
    -0.14
    ahy
    -0.14
    acie
    -0.14
    ifest
    -0.14
    enor
    -0.14
    POSITIVE LOGITS
     directly
    0.27
     actual
    0.25
     explicitly
    0.23
     necessarily
    0.23
     specifically
    0.22
     direct
    0.21
     exact
    0.21
    actual
    0.21
     formal
    0.20
     formally
    0.20
    Activations Density 0.128%

    No Known Activations