INDEX

Explanations

Java data structures and collections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

cef

-0.16

hausen

-0.15

ultz

-0.14

ÄŁan

-0.14

 Pulitzer

-0.14

 Barth

-0.14

piler

-0.13

Ä±lÄ±ÄŁÄ±yla

-0.13

silent

-0.13

egan

-0.13

POSITIVE LOGITS

(?:

0.16

izza

0.15

.iterator

0.15

Iterator

0.15

 åħī

0.14

akis

0.14

çĶ³åįļ

0.14

ovic

0.13

tel

0.13

Activations Density 0.003%

Java data structures and collections

No Comments

No Known Activations