INDEX

Explanations

references to the concept of "under" or "below."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

vely

-0.17

stakes

-0.15

udo

-0.14

eldon

-0.14

eniz

-0.14

ikit

-0.14

deaux

-0.14

çĻ¼

-0.13

steller

-0.13

iful

-0.13

POSITIVE LOGITS

lie

0.20

 patron

0.19

 guise

0.18

neath

0.17

arken

0.17

 influence

0.16

rido

0.16

 ausp

0.16

oba

0.15

 pseud

0.15

Activations Density 0.004%

references to the concept of "under" or "below."

No Comments

No Known Activations