© 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. 22-LLAMASCOPE-RES-32K
    11. 10888
    Prev
    Next
    INDEX
    Explanations

    references to meetings and collaborative events involving multiple parties, especially regarding education and women's empowerment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥĨãĥ«
    -0.14
    á»ĵn
    -0.14
    ắn
    -0.14
     बनन
    -0.14
    plorer
    -0.14
     bá»ı
    -0.13
    çĶ·åŃIJ
    -0.13
    issen
    -0.13
    consulta
    -0.13
    ÑĤаб
    -0.13
    POSITIVE LOGITS
     representatives
    0.54
     representative
    0.40
     Representatives
    0.38
    represent
    0.38
    Represent
    0.35
    代表
    0.33
     reps
    0.32
     representa
    0.32
     representations
    0.31
     deleg
    0.31
    Activations Density 0.183%

    No Known Activations