INDEX

Explanations

phrases related to evidence and its application 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 @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

pper

-0.16

ate

-0.15

aldo

-0.15

Ð½Ð¸Ð¼Ð°ÐµÑĤ

-0.15

lein

-0.15

isi

-0.14

igel

-0.14

ue

-0.14

swick

-0.14

/fw

-0.14

POSITIVE LOGITS

lessly

0.18

UILTIN

0.17

BuilderFactory

0.16

tam

0.15

eman

0.15

itious

0.15

onso

0.15

 evidence

0.15

iveness

0.15

Activations Density 0.036%

phrases related to evidence and its application in various contexts

No Comments

No Known Activations