INDEX

Explanations

instances of the hash symbol and accompanying numerical values in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

iÄįka

-0.17

ISCO

-0.16

jar

-0.16

uset

-0.15

uC

-0.15

inode

-0.14

abay

-0.14

lette

-0.14

hrad

-0.13

feld

-0.13

POSITIVE LOGITS

avana

0.18

ãĥ¼ãĥ«

0.16

 sino

0.16

ÏħÏĩ

0.15

ahlen

0.15

ald

0.14

Ð°Ð½ÑĤÐ°

0.14

cra

0.14

 Preservation

0.14

logan

0.14

Activations Density 0.002%

instances of the hash symbol and accompanying numerical values in the text

No Comments

No Known Activations