INDEX

Explanations

references to notable historical places or landmarks

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

oste

-0.18

china

-0.15

olest

-0.15

Ä±mÄ±za

-0.15

ohon

-0.14

LEM

-0.14

 Eudicots

-0.14

ilar

-0.14

.weixin

-0.13

ALLE

-0.13

POSITIVE LOGITS

.mdl

0.15

ãĥ¼ãĥª

0.15

affer

0.14

AAP

0.14

ullah

0.14

 Dial

0.14

YNAM

0.13

NING

0.13

cht

0.13

Pry

0.13

Activations Density 0.377%

references to notable historical places or landmarks

No Comments

No Known Activations