INDEX

Explanations

instances of interviews or mentions of interviews with individuals

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

Å¡t

-0.16

ioc

-0.16

yat

-0.15

æĪ

-0.14

 Ð»Ð¸ÑĪ

-0.14

_guess

-0.14

 envelope

-0.14

bar

-0.14

ÐµÑĢÐ¶

-0.14

POSITIVE LOGITS

eldon

0.17

INGER

0.16

inger

0.16

ingers

0.15

rick

0.15

linger

0.14

á»Ĩ

0.14

ÅĻÃŃz

0.14

fone

0.14

åĽº

0.14

Activations Density 0.030%

instances of interviews or mentions of interviews with individuals

No Comments

No Known Activations