© 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. 9451
    Prev
    Next
    INDEX
    Explanations

    phrases related to truth and accuracy in statements or claims

    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
    fet
    -0.16
    tera
    -0.15
     lesser
    -0.14
     Benef
    -0.14
    IA
    -0.14
    ollower
    -0.14
    ugar
    -0.14
    ãģ¨ãģĵãĤį
    -0.13
    ought
    -0.13
    _EXPORT
    -0.13
    POSITIVE LOGITS
     true
    0.35
     correct
    0.34
    true
    0.33
     accuracy
    0.33
     accurate
    0.33
    accur
    0.29
     Accuracy
    0.28
     truth
    0.28
     correctness
    0.28
    accuracy
    0.28
    Activations Density 0.205%

    No Known Activations