© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-32K
    11. 16083
    Prev
    Next
    INDEX
    Explanations

    instances where individuals acknowledge or confess to their actions or beliefs

    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
    Ñĩи
    -0.15
    ombie
    -0.15
    aub
    -0.14
    ¶Į
    -0.14
    ç´Ļ
    -0.14
    uos
    -0.14
     vite
    -0.14
    ibar
    -0.14
    apult
    -0.14
    iveau
    -0.14
    POSITIVE LOGITS
     admitted
    0.22
     defeat
    0.20
     admits
    0.20
     admission
    0.19
     having
    0.19
    æĸĻ
    0.17
     admit
    0.17
     Admission
    0.17
     comp
    0.16
    /disc
    0.16
    Activations Density 0.035%

    No Known Activations