INDEX

Explanations

phrases that indicate the variety or abundance of options

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

oven

-0.21

ousse

-0.17

lege

-0.17

mag

-0.15

eli

-0.15

bot

-0.15

flt

-0.14

overn

-0.14

exp

-0.14

IMS

-0.14

POSITIVE LOGITS

ebek

0.17

iferay

0.17

alse

0.15

_deinit

0.15

essa

0.15

XE

0.14

anner

0.14

geÃ§

0.14

 kÃª

0.14

tempt

0.14

Activations Density 0.042%

phrases that indicate the variety or abundance of options

No Comments

No Known Activations