INDEX

Explanations

phrases indicating problems or challenges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 favour

-0.15

 favor

-0.14

inne

-0.14

ãĥ³ãĥķ

-0.14

AYER

-0.14

postcode

-0.14

Ed

-0.14

/cal

-0.14

kÄ±n

-0.14

POSITIVE LOGITS

opak

0.19

cht

0.17

trap

0.16

mÃ©

0.16

ance

0.15

ifes

0.15

bjerg

0.15

ival

0.15

clus

0.15

ares

0.15

Activations Density 0.381%

phrases indicating problems or challenges

No Comments

No Known Activations