INDEX

Explanations

references to "franchise" and related terms 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 @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

rian

-0.20

aska

-0.16

pha

-0.15

imits

-0.15

chas

-0.15

itz

-0.14

obe

-0.14

gth

-0.14

asti

-0.14

ABA

-0.14

POSITIVE LOGITS

 borderTop

0.16

 Hardy

0.15

íĳ¸

0.14

eye

0.14

tac

0.14

uentes

0.14

YPRE

0.14

ement

0.14

 Ramos

0.13

Activations Density 0.006%

references to "franchise" and related terms in various contexts

No Comments

No Known Activations