INDEX

Explanations

instances of the word "Ju" in various forms

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

alom

-0.17

une

-0.16

yal

-0.15

Ã§e

-0.15

alic

-0.14

acman

-0.14

ACLE

-0.14

Protected

-0.14

tuÄŁ

-0.14

Wid

-0.13

POSITIVE LOGITS

lobs

0.15

 Trev

0.15

ä¼Ŀ

0.14

DM

0.14

ty

0.14

anko

0.14

0.13

æ¬ł

0.13

DT

0.13

Activations Density 0.002%

instances of the word "Ju" in various forms

No Comments

No Known Activations