INDEX

Explanations

occurrences of specific historical years or dates

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

scr

-0.15

REL

-0.14

Ĭ

-0.14

.wr

-0.14

abis

-0.14

ettel

-0.13

itemName

-0.13

papers

-0.13

ixin

-0.13

ervlet

-0.13

POSITIVE LOGITS

ernaut

0.16

andel

0.14

Î´Ïħ

0.14

Scope

0.14

 dÃ¢n

0.14

æĻ´

0.13

cmc

0.13

agram

0.13

hma

0.13

 Incontri

0.13

Activations Density 0.024%

occurrences of specific historical years or dates

No Comments

No Known Activations