INDEX

Explanations

specific characters or symbols, likely related to formatting or special characters in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

lick

-0.18

lear

-0.18

reated

-0.17

oms

-0.15

Ã©ri

-0.15

ÑģÑĤÑİ

-0.15

lasses

-0.15

li

-0.15

quir

-0.15

loth

-0.14

POSITIVE LOGITS

irk

0.21

zer

0.20

elem

0.18

enz

0.17

enn

0.17

igans

0.17

enna

0.17

elage

0.17

icer

0.16

ister

0.16

Activations Density 0.005%

specific characters or symbols, likely related to formatting or special characters in text

No Comments

No Known Activations