INDEX

Explanations

the name "Ernest" 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 @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

Î½Î¹

-0.16

Rao

-0.15

ttp

-0.15

iera

-0.15

ocup

-0.15

mÃ©

-0.14

apot

-0.14

azu

-0.14

gles

-0.14

POSITIVE LOGITS

ine

0.22

0.17

INE

0.16

olen

0.16

hausen

0.16

akers

0.15

Ej

0.15

oldem

0.14

linger

0.14

olean

0.14

Activations Density 0.009%

the name "Ernest" in various contexts

No Comments

No Known Activations