INDEX

Explanations

specific U.S. state abbreviations

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

-0.16

ently

-0.15

str

-0.15

ucks

-0.14

 Jensen

-0.14

 cour

-0.14

 cuales

-0.14

[s

-0.14

POSITIVE LOGITS

 æ¬

0.17

à¹Ĥà¸Ĭ

0.16

ÐµÑħ

0.16

odore

0.15

anche

0.15

celik

0.15

jeta

0.15

ichni

0.15

oku

0.15

ictionary

0.14

Activations Density 0.088%

specific U.S. state abbreviations

No Comments

No Known Activations