INDEX

Explanations

specific letters or symbols within the text

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

aggi

-0.17

inned

-0.15

EDITOR

-0.15

ypi

-0.14

oins

-0.14

alc

-0.14

inq

-0.14

.cloudflare

-0.14

VILLE

-0.14

ippi

-0.14

POSITIVE LOGITS

ivel

0.20

ely

0.19

enny

0.17

elyn

0.17

ogy

0.17

ELY

0.16

ester

0.16

ç§ģ

0.15

iben

0.15

kor

0.15

Activations Density 0.002%

specific letters or symbols within the text

No Comments

No Known Activations