INDEX

Explanations

phrases related to company evaluations and reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

anden

-0.16

ettel

-0.15

oda

-0.15

aka

-0.15

 tá»

-0.14

 dÃ¼

-0.14

 wasted

-0.14

isson

-0.13

untu

-0.13

ounding

-0.13

POSITIVE LOGITS

run

0.32

 operated

0.26

run

0.24

 founded

0.22

 owned

0.22

 solvent

0.21

-run

0.21

 operating

0.20

Run

0.20

Run

0.19

Activations Density 0.235%

phrases related to company evaluations and reports

No Comments

No Known Activations