INDEX

Explanations

references to the concept of "drag" in various contexts

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ariat

-0.21

acha

-0.17

dust

-0.16

cken

-0.16

cher

-0.15

avage

-0.15

ilar

-0.15

ãģ£ãģ¡

-0.15

chant

-0.15

anity

-0.15

POSITIVE LOGITS

ged

0.28

ging

0.26

 queen

0.23

gable

0.22

gin

0.22

gers

0.22

GING

0.22

STER

0.21

ster

0.21

 queens

0.21

Activations Density 0.008%

references to the concept of "drag" in various contexts

No Known Activations