© 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. 30-LLAMASCOPE-RES-32K
    11. 5019
    Prev
    Next
    INDEX
    Explanations

    suffixes related to demographic or ethnic identifiers and their statistical representations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    baugh
    -0.19
    otr
    -0.15
    issions
    -0.15
    adel
    -0.15
    éį
    -0.15
     =============================================================================↵
    -0.14
     Dos
    -0.14
    eks
    -0.14
    ustral
    -0.14
    iko
    -0.14
    POSITIVE LOGITS
    alette
    0.16
    MethodInfo
    0.16
    386
    0.16
    ourke
    0.16
    Mi
    0.14
     Arn
    0.14
     Curry
    0.14
    PCR
    0.14
    mi
    0.14
    è£ģ
    0.14
    Activations Density 0.011%

    No Known Activations