INDEX

Explanations

terms associated with identifying issues or problems

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

ramework

-0.16

estre

-0.15

áº¡ch

-0.15

ãĥ³ãĤº

-0.14

weets

-0.14

ht

-0.14

 Terrace

-0.14

 ÑĥÐ¼Ð¾Ð²Ð°Ñħ

-0.14

 Region

-0.13

é¼

-0.13

POSITIVE LOGITS

0.18

usat

0.15

GM

0.15

Weekly

0.14

é¾Ļ

0.14

McB

0.14

DMA

0.14

 Execution

0.14

Activations Density 0.017%

terms associated with identifying issues or problems

No Comments

No Known Activations