INDEX

Explanations

expressions of hesitation and uncertainty in dialogue

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Conway

-0.17

asher

-0.16

 Concord

-0.15

'aut

-0.15

ictor

-0.14

Ð¿Ð¾ÑĢ

-0.14

 åıĪ

-0.14

ald

-0.14

_plugins

-0.14

laz

-0.13

POSITIVE LOGITS

 actual

0.23

 actually

0.19

actual

0.18

å®ŀéĻħ

0.18

 obviously

0.17

 Actual

0.17

Actual

0.17

Actually

0.17

ERA

0.16

actually

0.16

Activations Density 0.241%

expressions of hesitation and uncertainty in dialogue

No Comments

No Known Activations