INDEX

Explanations

instances of the word "thoroughly" in various contexts

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

 Becker

-0.16

 Mans

-0.15

Ans

-0.14

uell

-0.14

ital

-0.14

gal

-0.14

uel

-0.14

POSITIVE LOGITS

isay

0.17

oplay

0.15

dna

0.15

 SALE

0.15

 Sale

0.14

ÙĤØ¯Ø±

0.14

ç§¯

0.14

abo

0.14

icont

0.14

ijke

0.14

Activations Density 0.003%

instances of the word "thoroughly" in various contexts

No Comments

No Known Activations