INDEX

Explanations

phrases indicating user navigation or location on a website

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

oro

-0.18

?↵↵↵↵↵↵

-0.16

iture

-0.16

enkins

-0.15

okie

-0.15

áº¡c

-0.15

oundingBox

-0.15

isor

-0.14

.ua

-0.14

itar

-0.14

POSITIVE LOGITS

::

0.19

 Â»

0.19

because

0.18

 Skip

0.18

 because

0.18

agger

0.16

Because

0.15

Â»

0.15

Home

0.15

 Home

0.15

Activations Density 0.001%

phrases indicating user navigation or location on a website

No Comments

No Known Activations