INDEX

Explanations

phrases indicating actions or elements that happen behind the scenes

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

æľĽ

-0.15

istro

-0.14

kle

-0.14

USR

-0.14

ç«ĭ

-0.14

 ç«ĭ

-0.14

_fwd

-0.13

 Superv

-0.13

indle

-0.13

rist

-0.13

POSITIVE LOGITS

 behind

1.03

 Behind

0.86

Behind

0.77

beh

0.65

 backstage

0.51

 achter

0.48

 underlying

0.47

 backend

0.44

 Ù¾Ø´Øª

0.40

_beh

0.37

Activations Density 0.231%

phrases indicating actions or elements that happen behind the scenes

No Comments

No Known Activations