INDEX

Explanations

references to specific seasons or episodes of a television show, along with demographic beliefs and statistics related to adults in New York City

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

.ly

-0.17

ollo

-0.16

pai

-0.15

PLY

-0.14

Helvetica

-0.14

olon

-0.14

Erk

-0.13

EXTERN

-0.13

ripple

-0.13

 rumpe

-0.13

POSITIVE LOGITS

.ManyToMany

0.16

å±±å¸Ĥ

0.15

anlÄ±

0.14

ovich

0.14

 millenn

0.14

eson

0.13

vester

0.13

ifax

0.13

iÄħ

0.13

 ActionTypes

0.13

Activations Density 0.103%

references to specific seasons or episodes of a television show, along with demographic beliefs and statistics related to adults in New York City

No Comments

No Known Activations