INDEX

Explanations

instances of the phrase "I mean" used to express clarification or emphasis in discourse

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

AGMA

-0.16

 Beled

-0.16

kal

-0.16

visor

-0.15

Ã¡mara

-0.15

chner

-0.15

blo

-0.14

aland

-0.14

 automÃ¡t

-0.14

(çģ«

-0.14

POSITIVE LOGITS

richt

0.16

OLON

0.15

APPER

0.15

 litter

0.14

isto

0.13

.dropdown

0.13

Å¾iv

0.13

pillar

0.13

Activations Density 0.014%

instances of the phrase "I mean" used to express clarification or emphasis in discourse

No Comments

No Known Activations