INDEX

Explanations

mentions of individuals or entities along with numerical identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

uard

-0.16

Pocket

-0.16

mobx

-0.15

bour

-0.15

KHR

-0.14

Å¸

-0.14

itore

-0.14

ern

-0.14

zioni

-0.14

fony

-0.14

POSITIVE LOGITS

 Class

0.17

 magna

0.16

å¿ħ

0.15

 sooner

0.15

 class

0.14

Ð¼Ð°ÑĤÐ¸

0.14

 Rosenstein

0.14

owa

0.14

 Exercise

0.14

://'

0.13

Activations Density 0.009%

mentions of individuals or entities along with numerical identifiers

No Comments

No Known Activations