INDEX

Explanations

instances of the word "recite" and its variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

loat

-0.16

utan

-0.16

 Gros

-0.15

ESC

-0.15

Î²Î¬

-0.14

à¸£à¸°

-0.14

rie

-0.13

 Extensions

-0.13

lds

-0.13

]("

-0.13

POSITIVE LOGITS

hardt

0.17

macen

0.16

:class

0.15

ufen

0.14

aku

0.14

sdale

0.14

alles

0.14

ivery

0.14

Ã«n

0.14

 Shades

0.13

Activations Density 0.006%

instances of the word "recite" and its variations

No Comments

No Known Activations