INDEX

Explanations

references to mathematical propositions, theorems, and lemmas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

uther

-0.16

utters

-0.16

Pry

-0.15

utch

-0.14

quel

-0.14

errat

-0.14

uddy

-0.14

ictor

-0.14

quat

-0.14

uits

-0.14

POSITIVE LOGITS

 Camb

0.15

ints

0.15

URITY

0.14

 adel

0.14

 twins

0.14

 DISABLE

0.13

pup

0.13

anine

0.13

an

0.13

Activations Density 0.067%

references to mathematical propositions, theorems, and lemmas

No Comments

No Known Activations