© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 20-LLAMASCOPE-RES-32K
    11. 10329
    Prev
    Next
    INDEX
    Explanations

    specific nouns and adjectives, particularly related to places and descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Scre
    -0.14
    _UID
    -0.14
    GBT
    -0.13
    amba
    -0.13
    alk
    -0.13
     Heath
    -0.12
     âľ
    -0.12
    ÑĢим
    -0.12
    agar
    -0.12
    .Blocks
    -0.12
    POSITIVE LOGITS
    urr
    0.16
    osphere
    0.14
    ùa
    0.14
    203
    0.14
    ût
    0.14
    394
    0.13
    оÑĢаз
    0.13
    187
    0.13
    illage
    0.13
    itou
    0.12
    Activations Density 0.007%

    No Known Activations