© 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. 8-LLAMASCOPE-RES-32K
    6. 2160
    Prev
    Next
    INDEX
    Explanations

    promotional content and events related to books and authors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chin
    -0.15
    uffs
    -0.14
    vation
    -0.14
    irates
    -0.14
     Davidson
    -0.14
     Král
    -0.14
    alleries
    -0.14
    AINS
    -0.14
    uff
    -0.14
    verts
    -0.14
    POSITIVE LOGITS
    .IContainer
    0.15
    FRING
    0.14
    arily
    0.14
     Throne
    0.14
     ETA
    0.14
    ayan
    0.14
    gone
    0.13
    dsp
    0.13
    frey
    0.13
    osta
    0.13
    Activations Density 0.015%

    No Known Activations