INDEX

Explanations

phrases indicating the existence or presence of a subject, often associated with intentions or missions

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

anse

-0.17

StringValue

-0.16

getDoctrine

-0.16

ca

-0.15

RAY

-0.15

athing

-0.15

clr

-0.14

avery

-0.14

 cold

-0.14

POSITIVE LOGITS

INTR

0.14

 stabilized

0.14

shake

0.14

ldr

0.14

amp

0.14

edral

0.14

åĮĸ

0.14

offs

0.14

splash

0.13

ç²¾

0.13

Activations Density 0.122%

phrases indicating the existence or presence of a subject, often associated with intentions or missions

No Comments

No Known Activations