© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 16-LLAMASCOPE-RES-32K
    6. 7323
    Prev
    Next
    INDEX
    Explanations

    references to military training and qualifications

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    .volley
    -0.16
     guild
    -0.16
    ambi
    -0.16
    agner
    -0.15
    SGlobal
    -0.15
    isay
    -0.14
     Guild
    -0.14
    ÙĦÙĬÙĩ
    -0.14
    «a
    -0.14
     Platinum
    -0.14
    POSITIVE LOGITS
     cad
    0.21
     Recru
    0.18
     training
    0.18
     Cad
    0.17
     Military
    0.17
     military
    0.16
     uniform
    0.16
     recruiters
    0.16
    Cad
    0.16
     trainers
    0.16
    Activations Density 0.082%

    No Known Activations