© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10231
    Prev
    Next
    INDEX
    Explanations

    expressions of fear and concerns regarding safety

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
     Cann
    -0.18
    anni
    -0.17
    baugh
    -0.16
    oom
    -0.15
    itech
    -0.15
    릴
    -0.14
    oucher
    -0.14
    argo
    -0.14
    оваÑĢ
    -0.14
    565
    -0.14
    POSITIVE LOGITS
     safety
    0.19
     intimid
    0.19
     unprotected
    0.18
     threats
    0.18
     Safety
    0.18
     protection
    0.18
    å®īåħ¨
    0.18
     Protection
    0.17
    -threat
    0.17
    Safety
    0.17
    Activations Density 0.172%

    No Known Activations