© 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. 25-LLAMASCOPE-RES-32K
    11. 13402
    Prev
    Next
    INDEX
    Explanations

    themes related to accountability and responsibility in various contexts

    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
     Merlin
    -0.15
    335
    -0.15
    Ãło
    -0.15
    aterno
    -0.15
    akis
    -0.14
    lingen
    -0.14
    меÑĩ
    -0.14
     Ãľst
    -0.14
    -Origin
    -0.14
    LC
    -0.13
    POSITIVE LOGITS
     lies
    0.96
     lie
    0.94
     lying
    0.75
     Lies
    0.70
     Lie
    0.69
    lies
    0.65
    lie
    0.65
     lay
    0.63
     lied
    0.63
    Lie
    0.61
    Activations Density 0.360%

    No Known Activations