© 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. 8257
    Prev
    Next
    INDEX
    Explanations

    references to personal care and hygiene products

    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
    isini
    -0.17
    stag
    -0.15
     cons
    -0.15
    .bs
    -0.15
     Glasses
    -0.14
     resc
    -0.14
    rof
    -0.14
    astos
    -0.13
    noho
    -0.13
     customs
    -0.13
    POSITIVE LOGITS
     feminine
    0.28
     tooth
    0.27
     Dove
    0.26
     deter
    0.25
     Toilet
    0.24
     toilet
    0.23
     wipes
    0.23
     soap
    0.23
     raz
    0.23
     Tooth
    0.21
    Activations Density 0.198%

    No Known Activations