© 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. 15396
    Prev
    Next
    INDEX
    Explanations

    instances of the word "thought" and its variations, suggesting a focus on cognition and reflection

    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
    eview
    -0.16
    hangi
    -0.15
    ierung
    -0.15
    oky
    -0.15
    noop
    -0.15
    ucha
    -0.14
    uze
    -0.14
    ERY
    -0.14
    aken
    -0.14
    ols
    -0.14
    POSITIVE LOGITS
    fully
    0.30
    fulness
    0.29
    lessly
    0.21
    ful
    0.20
    crime
    0.18
    象
    0.18
    -about
    0.18
     prov
    0.18
    FUL
    0.18
    bare
    0.17
    Activations Density 0.034%

    No Known Activations