INDEX

Explanations

references to legal or regulatory frameworks

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ÙĬÙĪÙĨ

-0.20

idal

-0.15

ecome

-0.14

 Sunder

-0.14

catalog

-0.14

ovy

-0.14

ampp

-0.14

_argv

-0.14

tright

-0.14

plier

-0.13

POSITIVE LOGITS

Gaw

0.16

tr

0.15

TEE

0.15

asu

0.15

addtogroup

0.15

 Hass

0.14

vero

0.14

ousse

0.14

guns

0.14

Non

0.14

Activations Density 0.006%

references to legal or regulatory frameworks

No Comments

No Known Activations