INDEX

Explanations

scenes depicting human interaction in a tense or dramatic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

yb

-0.15

cker

-0.15

ma

-0.15

 meas

-0.14

 accident

-0.14

coop

-0.14

 Bers

-0.14

imus

-0.13

 goog

-0.13

gro

-0.13

POSITIVE LOGITS

0.20

 Shooter

0.16

addtogroup

0.16

phylum

0.16

Ã¡vÄĽ

0.14

å¯

0.14

ispecies

0.14

Ã¼ÅŁ

0.13

 discrimin

0.13

quia

0.13

Activations Density 0.217%

scenes depicting human interaction in a tense or dramatic context

No Comments

No Known Activations