INDEX

Explanations

phrases that introduce or reference conditions, situations, or evidence related to various topics

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

ãĥŃãĥ¼

-0.17

une

-0.16

lt

-0.15

yle

-0.15

UNE

-0.15

æĹ¦

-0.14

ãģĵ

-0.14

 indiv

-0.14

una

-0.14

 falls

-0.13

POSITIVE LOGITS

 sake

0.17

tridge

0.17

 reason

0.17

.reason

0.16

 purposes

0.16

xcb

0.15

è¹

0.14

odyn

0.14

anto

0.14

rie

0.14

Activations Density 0.078%

phrases that introduce or reference conditions, situations, or evidence related to various topics

No Comments

No Known Activations