© 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. 17-LLAMASCOPE-RES-32K
    11. 30105
    Prev
    Next
    INDEX
    Explanations

    negations or contradictions in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÏĥÏĢ
    -0.17
    adr
    -0.16
    aÅĻ
    -0.15
    ute
    -0.15
    acie
    -0.15
    ikel
    -0.15
    ancel
    -0.15
     kork
    -0.15
    anta
    -0.14
    ylon
    -0.14
    POSITIVE LOGITS
     exact
    0.25
     exactly
    0.24
     directly
    0.24
     explicitly
    0.22
     necessarily
    0.20
     perfect
    0.20
     actual
    0.20
     strictly
    0.19
     precisely
    0.19
     literal
    0.19
    Activations Density 0.146%

    No Known Activations