© 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. 15-LLAMASCOPE-RES-32K
    11. 2979
    Prev
    Next
    INDEX
    Explanations

    references to intelligence or security-related positions within a bureaucratic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Atomic
    -0.17
    aload
    -0.15
    obierno
    -0.15
    aises
    -0.15
    bish
    -0.15
    æ±Ĥè´Ń
    -0.15
    arnation
    -0.15
     Ownership
    -0.15
     committee
    -0.14
    ůr
    -0.14
    POSITIVE LOGITS
    iaux
    0.18
     civil
    0.17
     Civil
    0.17
     feeder
    0.16
     hob
    0.15
    .argument
    0.15
     gazet
    0.15
    asher
    0.15
     h
    0.15
    ONUS
    0.14
    Activations Density 0.134%

    No Known Activations