INDEX

Explanations

numerical percentages related to thresholds or benchmarks in various contexts

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

ting

-0.19

olley

-0.16

Uhr

-0.16

urity

-0.15

cor

-0.15

Ã©gor

-0.15

nar

-0.14

gor

-0.14

.OnClickListener

-0.14

igue

-0.14

POSITIVE LOGITS

Ø©

0.18

iness

0.16

ishly

0.15

aviest

0.15

zeitig

0.15

Ø¡

0.15

zeug

0.15

rd

0.15

lund

0.15

0.14

Activations Density 0.112%

numerical percentages related to thresholds or benchmarks in various contexts

No Comments

No Known Activations