INDEX

Explanations

instances of the word "see" and its variants, indicating a focus on observation or perception

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

cko

-0.17

.Builder

-0.15

ilogy

-0.15

zman

-0.14

_GENERIC

-0.14

bject

-0.14

XE

-0.13

 Demir

-0.13

uh

-0.13

cpt

-0.13

POSITIVE LOGITS

 whether

0.23

whether

0.16

how

0.16

 Whether

0.14

 Relief

0.14

 *)((

0.14

AML

0.14

 ìĤ¬íķŃ

0.14

aed

0.14

Whether

0.13

Activations Density 0.026%

instances of the word "see" and its variants, indicating a focus on observation or perception

No Comments

No Known Activations