© 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. 14-LLAMASCOPE-RES-32K
    11. 7899
    Prev
    Next
    INDEX
    Explanations

    concepts related to power, abilities, and energy dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    amac
    -0.20
    pollo
    -0.15
    ÏĦί
    -0.15
    lej
    -0.14
    asses
    -0.14
    ãģ®ãģĮ
    -0.14
     McM
    -0.14
    ionales
    -0.14
    uegos
    -0.14
    ulle
    -0.14
    POSITIVE LOGITS
    SPATH
    0.13
    968
    0.13
     Garn
    0.13
    edic
    0.13
    SOURCE
    0.13
    969
    0.13
    yles
    0.13
     GUID
    0.13
    -DD
    0.13
    vrier
    0.13
    Activations Density 0.040%

    No Known Activations