INDEX

Explanations

phrases emphasizing possibilities and negative conditions or injustices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

uely

-0.16

ivec

-0.16

zell

-0.15

AXB

-0.14

oten

-0.14

ections

-0.14

 DXGI

-0.14

otr

-0.14

uur

-0.14

redits

-0.14

POSITIVE LOGITS

 Reeves

0.14

¤

0.14

 Dish

0.13

 Ð¾Ð±ÑıÐ·Ð°Ð½

0.13

phis

0.13

elson

0.13

pler

0.13

 sino

0.13

rieve

0.13

Activations Density 0.163%

phrases emphasizing possibilities and negative conditions or injustices

No Comments

No Known Activations