INDEX

Explanations

concepts related to different types of worlds, particularly dystopian and alternate realities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

eson

-0.15

Inset

-0.15

åĶ¯

-0.14

êµ°

-0.14

OLA

-0.14

TimeStamp

-0.14

 authentic

-0.13

ola

-0.13

py

-0.13

POSITIVE LOGITS

hq

0.17

iyon

0.17

kea

0.15

ãĥĭãĤ¢

0.15

evice

0.14

 Peyton

0.14

åħ¥ãĤĬ

0.14

tp

0.14

.opensource

0.14

freq

0.14

Activations Density 0.487%

concepts related to different types of worlds, particularly dystopian and alternate realities

No Comments

No Known Activations