INDEX

Explanations

references to transportation hubs, specifically terminals and towers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ese

-0.17

itan

-0.16

assin

-0.16

sing

-0.15

em

-0.15

 Middleton

-0.15

email

-0.15

ÙģØ§Ø¹

-0.14

letic

-0.14

lette

-0.14

POSITIVE LOGITS

rats

0.14

raits

0.14

ignum

0.14

.Term

0.14

erca

0.14

uzzi

0.14

buster

0.13

luÅ¾

0.13

oldt

0.13

ayne

0.13

Activations Density 0.005%

references to transportation hubs, specifically terminals and towers

No Comments

No Known Activations