INDEX

Explanations

references to individuals and their associated activities or professions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ialis

-0.15

xcf

-0.15

etur

-0.14

otti

-0.14

antis

-0.14

endency

-0.14

pto

-0.14

 ØµÙĪØ±

-0.14

holds

-0.14

POSITIVE LOGITS

anter

0.15

.setCode

0.15

 springfox

0.14

QRS

0.14

/XMLSchema

0.14

nad

0.13

GRES

0.13

 minimum

0.13

.Id

0.13

ossier

0.13

Activations Density 0.176%

references to individuals and their associated activities or professions

No Comments

No Known Activations