© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-32K
    6. 1216
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and concepts related to audio hardware and digital processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    assin
    -0.13
    ecta
    -0.13
    erosis
    -0.13
    jt
    -0.12
    memberOf
    -0.12
    assen
    -0.12
     Scho
    -0.12
    chter
    -0.12
    ÏĥÏĦε
    -0.12
    á»Ļc
    -0.12
    POSITIVE LOGITS
     frau
    0.14
    ovid
    0.14
    /WebAPI
    0.14
    -Allow
    0.13
    Invoker
    0.13
    OffsetTable
    0.13
     dÃŃ
    0.13
     UNUSED
    0.13
     kriz
    0.13
    /xhtml
    0.12
    Activations Density 0.106%

    No Known Activations