INDEX

Explanations

words and phrases related to adjectives and their grammatical roles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

aro

-0.20

aghan

-0.18

izon

-0.15

ussen

-0.15

 Olsen

-0.15

fen

-0.14

hardt

-0.14

mazon

-0.14

 Amer

-0.14

 Mate

-0.14

POSITIVE LOGITS

igham

0.17

ADIUS

0.17

eps

0.16

akk

0.15

cape

0.15

Wiki

0.15

andom

0.15

ivec

0.14

ÃĹ↵↵

0.14

.sponge

0.14

Activations Density 0.003%

words and phrases related to adjectives and their grammatical roles

No Comments

No Known Activations