INDEX

Explanations

references to specific companies and their executives or products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ditor

-0.15

Ã¡no

-0.15

BackPressed

-0.15

oard

-0.14

FFE

-0.14

bour

-0.14

 PROGMEM

-0.14

_cpp

-0.14

_ROUT

-0.14

znik

-0.14

POSITIVE LOGITS

 Group

0.22

Group

0.21

 Holding

0.20

 group

0.20

 company

0.17

isko

0.17

 GROUP

0.17

 Associates

0.17

group

0.16

igroup

0.16

Activations Density 0.524%

references to specific companies and their executives or products

No Comments

No Known Activations