INDEX

Explanations

proper nouns and entities, particularly focusing on names and brands

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

erate

-0.17

iesel

-0.14

 Fever

-0.14

OGLE

-0.14

èį

-0.13

spo

-0.13

 INCLUDE

-0.13

eah

-0.13

 Crossing

-0.13

POSITIVE LOGITS

 Bucc

0.14

Ð¾Ð½Ñĸ

0.14

âķĳ

0.14

ãģĹãĤĩ

0.14

StackNavigator

0.13

 Beans

0.13

[]={

0.13

çĲ³

0.13

çª

0.13

ãģİ

0.13

Activations Density 0.835%

proper nouns and entities, particularly focusing on names and brands

No Comments

No Known Activations