INDEX

Explanations

expressions that convey enjoyment and entertainment

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

esis

-0.16

orsch

-0.15

quo

-0.15

bindung

-0.15

ppard

-0.14

stial

-0.14

hood

-0.14

ors

-0.14

amage

-0.14

umper

-0.14

POSITIVE LOGITS

ghi

0.19

erals

0.18

nels

0.17

ctors

0.17

employed

0.15

icular

0.15

ëĭ¤ê°Ģ

0.15

-filled

0.15

nel

0.15

ÛĮÙĩ

0.15

Activations Density 0.028%

expressions that convey enjoyment and entertainment

No Comments

No Known Activations