© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-32K
    11. 4626
    Prev
    Next
    INDEX
    Explanations

    references to the number three and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    両
    -0.19
    nd
    -0.17
     twins
    -0.17
     twin
    -0.16
    opp
    -0.16
     halves
    -0.16
     BOTH
    -0.15
     beide
    -0.15
    assel
    -0.15
     both
    -0.14
    POSITIVE LOGITS
    rd
    0.26
     ä¸ī
    0.20
     trio
    0.20
    fold
    0.19
     Trio
    0.19
    reesome
    0.18
    rar
    0.17
     Triple
    0.17
     triple
    0.17
    Triple
    0.17
    Activations Density 0.450%

    No Known Activations