INDEX

Explanations

expressions of enjoyment or pleasure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ourcem

-0.15

ched

-0.15

ches

-0.15

enta

-0.14

unit

-0.14

.scalablytyped

-0.14

Ð½Ð¸ÑĩÐµÑģ

-0.14

ents

-0.13

upon

-0.13

POSITIVE LOGITS

ably

0.21

kle

0.16

 Ø·Ø±ÙĬÙĤ

0.15

/use

0.14

áº¯n

0.14

ìĽĥ

0.14

inkle

0.14

full

0.13

ovny

0.13

Activations Density 0.030%

expressions of enjoyment or pleasure

No Comments

No Known Activations