© 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. 16-LLAMASCOPE-RES-32K
    11. 21091
    Prev
    Next
    INDEX
    Explanations

    instances of rejection or refusal in decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Annotations
    -0.16
    ERRU
    -0.15
    clare
    -0.15
    ubo
    -0.15
    arkan
    -0.15
    loub
    -0.14
    asje
    -0.14
    ctl
    -0.14
    ;br
    -0.14
    ENCIL
    -0.14
    POSITIVE LOGITS
     offers
    0.24
    Reject
    0.23
     offer
    0.23
     Reject
    0.23
     reject
    0.23
     rejected
    0.23
     rejection
    0.23
    reject
    0.22
     offered
    0.22
     declined
    0.21
    Activations Density 0.125%

    No Known Activations