© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 24-LLAMASCOPE-RES-32K
    11. 18299
    Prev
    Next
    INDEX
    Explanations

    phrases related to personalization and customized gifts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    olean
    -0.17
    rote
    -0.15
    icana
    -0.15
    alette
    -0.14
    ãĤĪãģ³
    -0.14
    vox
    -0.14
    alse
    -0.14
    ÃŃna
    -0.13
    elez
    -0.13
    illisecond
    -0.13
    POSITIVE LOGITS
     custom
    0.25
     customization
    0.24
     Custom
    0.23
     personalize
    0.23
     personalized
    0.22
     Personal
    0.21
     personal
    0.21
     personalised
    0.21
     CUSTOM
    0.20
    /custom
    0.20
    Activations Density 0.064%

    No Known Activations