INDEX

Explanations

references to guidelines or rules related to policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

EventArgs

-0.14

èĦ±

-0.14

emat

-0.14

è§ī

-0.14

rome

-0.14

lian

-0.14

 bulletin

-0.13

rog

-0.13

isor

-0.13

 pres

-0.13

POSITIVE LOGITS

isters

0.17

ARC

0.17

urdy

0.16

ystore

0.16

forth

0.16

ettings

0.15

icensed

0.15

ough

0.15

parison

0.14

priv

0.14

Activations Density 0.004%

references to guidelines or rules related to policies

No Comments

No Known Activations