INDEX

Explanations

references to new projects, developments, and initiatives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ulong

-0.15

owe

-0.15

ossier

-0.15

ãĤ¤ãĥ³ãĥĪ

-0.15

des

-0.15

rou

-0.15

orns

-0.14

ëĭ¤ìļ´

-0.14

reh

-0.14

DRV

-0.13

POSITIVE LOGITS

ard

0.15

skÃ½

0.15

ihan

0.14

itan

0.14

 footprint

0.14

ARD

0.14

itect

0.13

 upcoming

0.13

 const

0.13

rand

0.13

Activations Density 0.512%

references to new projects, developments, and initiatives

No Comments

No Known Activations