© 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. 27-LLAMASCOPE-RES-32K
    11. 11444
    Prev
    Next
    INDEX
    Explanations

    conditional phrases that pose questions about various scenarios or choices

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     niet
    -0.20
     both
    -0.20
     neither
    -0.20
     nicht
    -0.20
     not
    -0.19
     tidak
    -0.18
     не
    -0.17
     ikke
    -0.17
     deÄŁil
    -0.17
     nejen
    -0.17
    POSITIVE LOGITS
    whether
    0.20
     whether
    0.18
    Whether
    0.18
     ultimately
    0.17
     WHETHER
    0.17
     Whether
    0.17
    æĺ¯åIJ¦
    0.16
     zda
    0.16
     simple
    0.15
     simply
    0.15
    Activations Density 0.068%

    No Known Activations