INDEX

Explanations

phrases associated with operational instructions and conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

asher

-0.15

aces

-0.15

ULSE

-0.15

ertz

-0.14

ÐľÐŀ

-0.14

 Projection

-0.14

 Helena

-0.13

Cancelable

-0.13

ÏĥÏĦÎ±ÏĥÎ·

-0.13

 tack

-0.13

POSITIVE LOGITS

 trigger

0.23

 triggered

0.20

 triggers

0.20

 triggering

0.19

 Trigger

0.18

(trigger

0.18

trigger

0.18

.trigger

0.17

anut

0.17

Trigger

0.17

Activations Density 0.216%

phrases associated with operational instructions and conditions

No Comments

No Known Activations