© 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. 29-LLAMASCOPE-RES-32K
    11. 18328
    Prev
    Next
    INDEX
    Explanations

    words related to construction and progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.29.hook_resid_post
    Hook Layer
    29
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apult
    -0.15
    ãĥ³ãĥĩ
    -0.15
    NCY
    -0.14
    apur
    -0.14
    maktan
    -0.14
    chooser
    -0.14
    ä»°
    -0.14
     Gratuit
    -0.13
    ppo
    -0.13
    ologi
    -0.13
    POSITIVE LOGITS
     progress
    1.22
     Progress
    1.10
    progress
    1.05
    Progress
    0.99
    -progress
    0.92
    _progress
    0.91
    è¿Ľ
    0.88
    .progress
    0.87
     progresses
    0.82
    (progress
    0.80
    Activations Density 0.153%

    No Known Activations