INDEX

Explanations

discussions surrounding environmental policies and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

asio

-0.16

-0.15

éĩ

-0.15

sei

-0.14

istra

-0.14

 disparate

-0.13

&E

-0.13

Responder

-0.13

—

-0.13

tz

-0.13

POSITIVE LOGITS

 Scalar

0.17

–↵↵

0.15

 spatial

0.15

 Weber

0.15

ughter

0.15

 legit

0.15

 actors

0.15

oliberal

0.15

 [âĢ¦]↵↵

0.15

 scalar

0.14

Activations Density 0.295%

discussions surrounding environmental policies and regulations

No Comments

No Known Activations