INDEX

Explanations

occurrences of the letter "a" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

th

-0.19

defgroup

-0.16

only

-0.15

iem

-0.15

orough

-0.15

aan

-0.15

SizeMode

-0.14

 hood

-0.14

Only

-0.14

insi

-0.14

POSITIVE LOGITS

 dozen

0.21

 acre

0.20

 foot

0.18

edla

0.18

-do

0.17

 Foot

0.16

 mile

0.15

 hour

0.15

do

0.15

Dek

0.15

Activations Density 0.026%

occurrences of the letter "a" in various contexts

No Comments

No Known Activations