INDEX

Explanations

references to wetlands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ØºÙĨ

-0.17

Úĺ

-0.15

Tos

-0.15

lian

-0.15

Transpose

-0.14

 Soft

-0.14

Ð¾Ð´Ð¾

-0.14

naissance

-0.14

idon

-0.13

esseract

-0.13

POSITIVE LOGITS

pir

0.18

upt

0.15

 Abrams

0.15

0.14

Ã¼st

0.14

edBy

0.14

udi

0.14

Kem

0.14

Î¼ÏĢÎ¿

0.13

Activations Density 0.006%

references to wetlands

No Comments

No Known Activations