© 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. 14-LLAMASCOPE-RES-32K
    6. 22478
    Prev
    Next
    INDEX
    Explanations

    references to fixed schedules and time-related constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anes
    -0.19
    682
    -0.15
    ">//
    -0.15
    quin
    -0.15
    otec
    -0.15
    .www
    -0.15
    clipse
    -0.14
    dance
    -0.14
    ÙĦÙĬÙĩ
    -0.14
    izzle
    -0.13
    POSITIVE LOGITS
     fixed
    0.30
    fixed
    0.28
     Fixed
    0.26
    Fixed
    0.26
    åĽºå®ļ
    0.25
    -fixed
    0.25
    _fixed
    0.24
    FIX
    0.23
     FIXED
    0.23
    .fixed
    0.20
    Activations Density 0.219%

    No Known Activations