INDEX

Explanations

phrases that indicate an association with conditions or activities common in various fields, including business and social interactions

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

midd

-0.14

Tot

-0.14

permit

-0.14

icc

-0.14

iska

-0.13

stract

-0.13

.abstract

-0.13

 Corner

-0.13

entes

-0.13

 Grey

-0.13

POSITIVE LOGITS

 both

0.19

alion

0.18

 either

0.17

both

0.17

stÃ¤nd

0.15

 neither

0.15

arness

0.15

chs

0.15

_BOTH

0.14

 morb

0.14

Activations Density 0.125%

phrases that indicate an association with conditions or activities common in various fields, including business and social interactions

No Comments

No Known Activations