© 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. 18-LLAMASCOPE-RES-32K
    11. 3157
    Prev
    Next
    INDEX
    Explanations

    references to specific entities or identifiers within structured data, such as names and associated values

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zel
    -0.12
    nez
    -0.11
    &m
    -0.10
    NIC
    -0.10
    ãĥ¼ãĥ«
    -0.10
    orte
    -0.10
    pez
    -0.10
    ï¿
    -0.10
    furt
    -0.10
     fucks
    -0.10
    POSITIVE LOGITS
    uddy
    0.13
     “
    0.12
    Ìģt
    0.12
     destinationViewController
    0.12
    liers
    0.12
     âĢ¦↵
    0.11
    âĢ¦↵
    0.11
    endum
    0.10
    оÑĢаÑı
    0.10
    isté
    0.10
    Activations Density 8.598%

    No Known Activations