INDEX

Explanations

elements related to spatial structures and orientations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

punkt

-0.15

(es

-0.15

uations

-0.15

ansas

-0.14

Ð°Ð»ÑĮÐ½Ðµ

-0.14

uable

-0.14

th

-0.14

ermen

-0.14

OLUTION

-0.13

 fois

-0.13

POSITIVE LOGITS

la

0.24

el

0.19

una

0.18

un

0.17

les

0.16

ìį¨

0.16

ween

0.15

ankan

0.15

 åĨĨ

0.15

æı

0.15

Activations Density 0.081%

elements related to spatial structures and orientations

No Comments

No Known Activations