INDEX

Explanations

references to the name "Jay" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ampion

-0.16

anon

-0.15

ydk

-0.14

nemonic

-0.14

inv

-0.14

imitives

-0.14

WARDED

-0.14

igen

-0.14

ãĤ¤ãĤº

-0.14

éĲĺ

-0.14

POSITIVE LOGITS

tog

0.17

rng

0.16

 seins

0.14

angl

0.14

AS

0.14

 Ottawa

0.14

walker

0.14

 itch

0.14

abol

0.13

Activations Density 0.008%

references to the name "Jay" in various contexts

No Comments

No Known Activations