© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-32K
    6. 30541
    Prev
    Next
    INDEX
    Explanations

    repeated references to specific entities or themes within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iao
    -0.17
    esto
    -0.16
     byÅĤo
    -0.15
    enzie
    -0.15
    otto
    -0.15
    pires
    -0.15
    cco
    -0.15
    enco
    -0.14
    _Impl
    -0.14
     tlak
    -0.14
    POSITIVE LOGITS
     misma
    0.28
     familia
    0.23
     mayorÃŃa
    0.23
     comunidad
    0.22
    zos
    0.22
     propia
    0.22
     ciudad
    0.22
     ép
    0.20
     Universidad
    0.20
     vida
    0.20
    Activations Density 0.028%

    No Known Activations