INDEX

Explanations

instances of uncertainty or conditionality expressed in sentences

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

 recently

-0.24

 Recently

-0.20

 lately

-0.20

 ÄĳÃ£

-0.19

Recently

-0.19

 bisher

-0.18

did

-0.18

_recent

-0.17

 å·²

-0.17

å·²

-0.16

POSITIVE LOGITS

izon

0.17

ion

0.16

0.15

iazza

0.15

steller

0.14

Io

0.14

 Rita

0.14

 desc

0.13

udo

0.13

ãĤĮãģ¦

0.13

Activations Density 0.077%

instances of uncertainty or conditionality expressed in sentences

No Comments

No Known Activations