INDEX

Explanations

references to work shifts and job-related experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

contest

-0.15

ãĥ³ãĥķ

-0.15

poon

-0.14

xCD

-0.14

ustos

-0.14

ÑĮÑİÑĤ

-0.13

isÃŃ

-0.13

imizer

-0.13

à¹ģà¸Ķà¸ĩ

-0.13

gress

-0.13

POSITIVE LOGITS

 shift

0.93

 shifts

0.87

shift

0.83

 Shift

0.82

Shift

0.81

-shift

0.78

 SHIFT

0.65

.shift

0.65

_shift

0.64

 shifted

0.64

Activations Density 0.194%

references to work shifts and job-related experiences

No Comments

No Known Activations