INDEX

Explanations

future-oriented verbs and expressions related to intention or prediction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ã±ana

-0.17

kla

-0.15

annes

-0.15

 doGet

-0.14

Ð°ÑĨÐ¸Ð¸

-0.14

.mx

-0.14

clearfix

-0.14

adal

-0.14

ëłī

-0.13

POSITIVE LOGITS

Ð¾ÑĢÐ¾Ð²

0.17

ãĤ¹ãĤ¿ãĥ¼

0.15

Ð°ÑĢÑĩ

0.14

ler

0.14

egg

0.14

ÑıÑģ

0.14

umar

0.14

èĢħ

0.14

ench

0.14

 thunder

0.14

Activations Density 0.175%

future-oriented verbs and expressions related to intention or prediction

No Comments

No Known Activations