INDEX

Explanations

references to locking and unlocking mechanisms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

asar

-0.20

ug

-0.16

ulfilled

-0.14

hound

-0.14

ula

-0.14

askan

-0.14

apur

-0.13

oval

-0.13

/gin

-0.13

altar

-0.13

POSITIVE LOGITS

 lock

0.19

Ã¡bado

0.19

 doors

0.18

(lock

0.16

 Doors

0.16

 locks

0.16

 door

0.15

 bootloader

0.15

 locking

0.15

ÎµÏĦ

0.14

Activations Density 0.035%

references to locking and unlocking mechanisms

No Comments

No Known Activations

references to locking and unlocking mechanisms

No Comments

No Known Activations