© 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. 10-LLAMASCOPE-RES-32K
    11. 3257
    Prev
    Next
    INDEX
    Explanations

    terms related to financial or economic impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .unpack
    -0.14
     nhiên
    -0.14
     Mesa
    -0.13
     WithEvents
    -0.13
    esz
    -0.13
     wild
    -0.13
    oloj
    -0.13
    kee
    -0.13
     Wild
    -0.12
     MOZ
    -0.12
    POSITIVE LOGITS
    ipc
    0.14
    éĻ£
    0.14
    änd
    0.14
    /meta
    0.14
     Combination
    0.14
    anitize
    0.13
    ạnh
    0.13
    ValuePair
    0.13
    ombre
    0.13
    urrection
    0.13
    Activations Density 0.072%

    No Known Activations