© 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. 19-LLAMASCOPE-RES-32K
    11. 32397
    Prev
    Next
    INDEX
    Explanations

    programming terms and identifiers related to object-oriented and database structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    å·ŀå¸Ĥ
    -0.15
    å±±å¸Ĥ
    -0.15
    .Tables
    -0.13
     件
    -0.11
    odcast
    -0.11
    ãĤīãģĹ
    -0.11
     Büyük
    -0.11
    ÑĢоÑģÑĤо
    -0.11
    оÑģÑĢед
    -0.11
    igli
    -0.11
    POSITIVE LOGITS
    ahl
    0.14
    ](
    0.13
    Ưá»
    0.13
    ]
    0.13
     Giles
    0.12
    #af
    0.12
    óż
    0.12
     Lester
    0.12
    eview
    0.12
    @nate
    0.11
    Activations Density 0.533%

    No Known Activations