INDEX

Explanations

place names and geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

thon

-0.18

conti

-0.15

igner

-0.15

§

-0.15

ema

-0.15

uzzi

-0.14

ouch

-0.14

ente

-0.14

ichen

-0.13

Ħĸ

-0.13

POSITIVE LOGITS

:System

0.17

 Gardner

0.15

isy

0.14

æĬĺ

0.14

-navbar

0.14

atri

0.14

è³Ģ

0.14

anford

0.14

Ð¾Ð²Ðµ

0.13

 decentralized

0.13

Activations Density 0.003%

place names and geographic locations

No Comments

No Known Activations