INDEX

Explanations

instances of the word "report" and its variations related to data and findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ehler

-0.17

borne

-0.16

erties

-0.15

more

-0.15

heart

-0.15

ery

-0.14

ic

-0.14

aler

-0.14

bourne

-0.14

ermal

-0.14

POSITIVE LOGITS

edly

0.26

à¸ªà¸Ķ

0.17

èĪĹ

0.17

ãĥ¥

0.17

orial

0.17

sdale

0.16

Ð¸ÑĪ

0.16

èĬ³

0.15

htable

0.15

getDb

0.15

Activations Density 0.065%

instances of the word "report" and its variations related to data and findings

No Comments

No Known Activations