© 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. 27-LLAMASCOPE-RES-32K
    6. 3293
    Prev
    Next
    INDEX
    Explanations

    references to notable people and events in sports and entertainment news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -L
    -0.19
    lsi
    -0.17
    alu
    -0.16
    ë°Ķ
    -0.16
    isser
    -0.16
    ÅĤaw
    -0.16
    osa
    -0.16
    _L
    -0.16
    LD
    -0.15
    elsen
    -0.15
    POSITIVE LOGITS
    ge
    0.19
     Georges
    0.17
    ãĤ¸ãĤª
    0.17
    γε
    0.16
    gon
    0.15
    ience
    0.15
    GIT
    0.15
    HQ
    0.15
    à¥Įà¤Ĥ
    0.14
    Ge
    0.14
    Activations Density 0.057%

    No Known Activations