INDEX

Explanations

code comments indicating documentation or descriptions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ares

-0.20

thon

-0.17

aled

-0.17

yr

-0.15

ils

-0.14

entials

-0.14

ande

-0.14

.define

-0.14

ote

-0.13

erva

-0.13

POSITIVE LOGITS

Ø©

0.14

Ø³ØªØ±

0.14

bishop

0.14

ffen

0.14

arium

0.14

.nlm

0.13

buyer

0.13

Pra

0.13

å¥Ī

0.13

Activations Density 0.017%

code comments indicating documentation or descriptions

No Comments

No Known Activations