INDEX

Explanations

references to companies or organizations involved in professional services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

illac

-0.15

icut

-0.14

pow

-0.14

okes

-0.14

imony

-0.14

avras

-0.14

ÎµÎ¯Î¿

-0.14

essler

-0.13

ettes

-0.13

POSITIVE LOGITS

Geb

0.15

unn

0.14

dale

0.14

 Bach

0.14

apur

0.14

0.13

apis

0.13

 Ridley

0.13

.nano

0.13

 POLITICO

0.13

Activations Density 0.002%

references to companies or organizations involved in professional services

No Comments

No Known Activations