INDEX

Explanations

variations of the word "Nederlands" and related terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 1-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ulp

-0.15

:UITableView

-0.14

æµ¦

-0.14

dry

-0.14

steller

-0.14

avel

-0.14

à¥įà¤

-0.14

uD

-0.14

awa

-0.13

rawer

-0.13

POSITIVE LOGITS

IPPING

0.15

branch

0.15

 Bloom

0.14

/renderer

0.14

ighbors

0.14

Ð½ÐµÐ½

0.14

 antim

0.14

arah

0.14

 branch

0.14

urtle

0.14

Activations Density 0.012%

variations of the word "Nederlands" and related terms

No Comments

No Known Activations