INDEX

Explanations

numerical identifiers or references 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 @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

anas

-0.16

-0.15

egg

-0.15

 tube

-0.15

 Tube

-0.15

-eye

-0.14

 relic

-0.14

 Äĳáº©y

-0.14

orrent

-0.14

-0.13

POSITIVE LOGITS

iams

0.18

ton

0.15

å¢

0.14

ocht

0.14

nonnull

0.14

 BATCH

0.14

IDES

0.14

å½¹

0.14

ufen

0.14

_BATCH

0.13

Activations Density 0.008%

numerical identifiers or references in the text

No Comments

No Known Activations