INDEX

Explanations

references to uncertainty or hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

utherland

-0.18

lsru

-0.17

-vs

-0.16

sv

-0.15

erece

-0.14

 Bones

-0.14

arÃŃa

-0.14

 åį

-0.14

((*

-0.14

aversable

-0.14

POSITIVE LOGITS

uble

0.16

\Configuration

0.15

-ignore

0.15

Ø§ÙĬÙĦ

0.15

 Casey

0.14

 chron

0.14

cron

0.14

 Premi

0.14

ãģĹãĤĩ

0.14

 Canter

0.14

Activations Density 0.065%

references to uncertainty or hypothetical scenarios

No Comments

No Known Activations