INDEX

Explanations

references to specific athletes or prominent sporting events

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

arning

-0.17

carousel

-0.15

ering

-0.15

esco

-0.14

 Hazard

-0.14

ihn

-0.14

 Mime

-0.14

AMI

-0.14

abeth

-0.14

arendra

-0.14

POSITIVE LOGITS

åľĪ

0.16

avity

0.14

gn

0.14

azel

0.14

undles

0.14

isyon

0.14

EMPL

0.14

 Screen

0.14

 Vernon

0.14

Ã¡no

0.13

Activations Density 0.409%

references to specific athletes or prominent sporting events

No Comments

No Known Activations