INDEX

Explanations

references to the name "Judah" and related variations, indicating a focus on this specific term within 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 @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ey

-0.17

ilha

-0.16

ton

-0.15

Ã¡lt

-0.15

ald

-0.15

 ActionTypes

-0.15

led

-0.15

ordin

-0.15

Ã¡ÅĻ

-0.14

 ÑĥÐ³Ð¾Ð´

-0.14

POSITIVE LOGITS

iciary

0.27

icial

0.26

gment

0.24

gement

0.24

ging

0.24

icious

0.23

jud

0.22

Jud

0.22

jud

0.20

gments

0.19

Activations Density 0.011%

references to the name "Judah" and related variations, indicating a focus on this specific term within various contexts

No Comments

No Known Activations