INDEX

Explanations

phrases related to possibility and capability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 somehow

-0.17

egl

-0.16

artner

-0.16

irs

-0.15

Probably

-0.15

hopefully

-0.14

unker

-0.14

lassen

-0.14

 probably

-0.14

Ð¼Ð¾Ð²ÑĸÑĢ

-0.14

POSITIVE LOGITS

 sometimes

0.29

sometimes

0.24

 Sometimes

0.23

be

0.22

ometimes

0.22

Sometimes

0.21

 range

0.19

 often

0.18

range

0.17

 either

0.16

Activations Density 0.183%

phrases related to possibility and capability

No Comments

No Known Activations

phrases related to possibility and capability

No Comments

No Known Activations