INDEX

Explanations

specific names and titles associated with notable individuals or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ãĤ£

-0.15

Î½Î¹

-0.14

ãĥ¼ãĥĭ

-0.13

pac

-0.13

ival

-0.13

IVAL

-0.13

 oluÅŁan

-0.12

oy

-0.12

odore

-0.12

&gt

-0.12

POSITIVE LOGITS

ernals

0.14

elter

0.14

AEA

0.14

ignon

0.13

indre

0.13

 nonatomic

0.13

undry

0.13

Ð±Ð°Ð²

0.13

instein

0.13

bach

0.12

Activations Density 0.014%

specific names and titles associated with notable individuals or events

No Comments

No Known Activations