INDEX

Explanations

occurrences of the word "Cron" in various forms, indicating a focus on a specific brand or terminology

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

ienne

-0.17

resse

-0.16

mond

-0.15

dash

-0.15

ages

-0.15

eel

-0.14

rics

-0.14

aged

-0.14

jing

-0.14

POSITIVE LOGITS

lund

0.20

enberg

0.20

enburg

0.19

yms

0.19

auer

0.18

.gb

0.18

borg

0.16

acher

0.16

qv

0.15

ocker

0.15

Activations Density 0.005%

occurrences of the word "Cron" in various forms, indicating a focus on a specific brand or terminology

No Comments

No Known Activations