INDEX

Explanations

references to specific individuals or characters 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 himself

-0.18

 Himself

-0.18

unga

-0.18

opr

-0.16

.libs

-0.15

ÐµÑĢÐ¶

-0.14

 nÃło

-0.14

 sÃ¡m

-0.14

ungi

-0.14

nÃŃ

-0.14

POSITIVE LOGITS

 alike

0.42

 respectively

0.33

 both

0.28

 themselves

0.28

 BOTH

0.25

both

0.25

 sowie

0.24

 ê°ģê°ģ

0.24

 serta

0.23

 their

0.23

Activations Density 0.236%

references to specific individuals or characters in various contexts

No Comments

No Known Activations