INDEX

Explanations

phrases related to breaking or setting records

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ummy

-0.15

ki

-0.15

Ki

-0.15

 Charlottesville

-0.14

 anon

-0.14

 Ø¬Ø§Ùħ

-0.14

onse

-0.14

 McMahon

-0.13

aroo

-0.13

utow

-0.13

POSITIVE LOGITS

hari

0.18

.nlm

0.16

 lastIndex

0.16

uesta

0.15

SPATH

0.15

.radians

0.14

eve

0.14

arta

0.14

_simps

0.14

ilmington

0.14

Activations Density 0.026%

phrases related to breaking or setting records

No Comments

No Known Activations