© 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. 27-LLAMASCOPE-RES-32K
    11. 12877
    Prev
    Next
    INDEX
    Explanations

    negative phrases or expressions, particularly those emphasizing denial or absence

    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
    cul
    -0.16
    æł·åŃIJ
    -0.16
    uj
    -0.15
    rape
    -0.15
    ty
    -0.15
    encers
    -0.15
    immers
    -0.15
    olik
    -0.15
    ikh
    -0.15
    ans
    -0.15
    POSITIVE LOGITS
     matter
    0.47
    matter
    0.38
     Matter
    0.31
     wonder
    0.30
     doubt
    0.29
     amount
    0.24
     sooner
    0.24
     one
    0.22
    论
    0.21
     two
    0.20
    Activations Density 0.042%

    No Known Activations