INDEX

Explanations

references to policies and their attributes in a coding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

swick

-0.18

isen

-0.15

anco

-0.15

ÙĪØ«

-0.15

ames

-0.15

.cgi

-0.14

 diseÃ±ador

-0.14

ãĥ¼ãĥĸ

-0.14

lico

-0.14

ungan

-0.14

POSITIVE LOGITS

esar

0.15

imet

0.15

 Stub

0.15

TestData

0.15

 Ipsum

0.14

.Mock

0.14

 Ø§ÙĦØªÙĪ

0.14

Stub

0.14

>Lorem

0.14

_ABC

0.14

Activations Density 0.033%

references to policies and their attributes in a coding context

No Comments

No Known Activations