INDEX

Explanations

occurrences of the word "introduction."

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

obe

-0.15

uela

-0.15

Sharper

-0.15

 Frontier

-0.15

oen

-0.14

inki

-0.14

vae

-0.14

Ð²Ð¾

-0.14

antan

-0.14

ova

-0.14

POSITIVE LOGITS

ductory

0.20

ezi

0.15

olley

0.15

strup

0.15

EMS

0.15

Å¼y

0.15

emarks

0.14

chyb

0.14

aliz

0.14

optgroup

0.14

Activations Density 0.019%

occurrences of the word "introduction."

No Comments

No Known Activations