INDEX

Explanations

terms related to environmental regulations and assessments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

 dist

-0.15

cola

-0.15

-0.14

ikal

-0.14

 attempted

-0.14

;height

-0.14

iage

-0.14

lobs

-0.14

-0.13

jac

-0.13

POSITIVE LOGITS

egral

0.18

yan

0.17

iske

0.16

izia

0.15

iu

0.15

 toxicity

0.15

oux

0.14

agedList

0.14

ru

0.14

lod

0.14

Activations Density 0.092%

terms related to environmental regulations and assessments

No Comments

No Known Activations