INDEX

Explanations

references to academic and professional organizations or institutions

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

gan

-0.17

PLACE

-0.16

noch

-0.15

nox

-0.15

gota

-0.15

ulle

-0.14

olv

-0.14

iado

-0.14

MLP

-0.14

vier

-0.13

POSITIVE LOGITS

 Wenger

0.14

ytut

0.14

onitor

0.14

Ð°Ð½Ð¸ÑĨ

0.14

arness

0.14

lyph

0.14

TECTED

0.13

 Sick

0.13

 Hacker

0.13

 Animalia

0.13

Activations Density 0.063%

references to academic and professional organizations or institutions

No Comments

No Known Activations