INDEX

Explanations

phrases related to corners and changes in location or direction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ĴĪ

-0.17

ewe

-0.16

ÑĩÐ½Ð¾

-0.15

cona

-0.14

Ð¾ÑĤÐ°

-0.14

æķ

-0.14

nit

-0.14

 Directions

-0.13

 ÙĨÙģ

-0.13

POSITIVE LOGITS

 corner

0.81

corner

0.66

 Corner

0.60

Corner

0.59

 corners

0.56

-corner

0.56

_corner

0.41

 bend

0.35

 turn

0.33

 comer

0.32

Activations Density 0.041%

phrases related to corners and changes in location or direction

No Comments

No Known Activations