© 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. 6-LLAMASCOPE-RES-32K
    6. 10832
    Prev
    Next
    INDEX
    Explanations

    brackets and braces indicating sections of mathematical expressions or algorithms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    engkap
    -0.16
    ryn
    -0.15
    Jud
    -0.15
    GRES
    -0.14
    ynes
    -0.14
    iyah
    -0.14
    ék
    -0.14
    ABCDEFGHIJKLMNOP
    -0.14
    ickey
    -0.14
    olume
    -0.14
    POSITIVE LOGITS
     Pit
    0.14
     wi
    0.14
    иÑĨ
    0.13
     Prompt
    0.13
     polar
    0.13
    ail
    0.13
    _definitions
    0.13
     Proud
    0.13
    .parsers
    0.13
    anto
    0.13
    Activations Density 0.008%

    No Known Activations