INDEX

Explanations

references to specific locations and events in stories

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

anten

-0.16

 batching

-0.14

ellido

-0.14

wu

-0.14

kee

-0.13

ImageContext

-0.13

quina

-0.13

åħ¶ä¸Ń

-0.13

etable

-0.13

table

-0.13

POSITIVE LOGITS

 When

0.18

 when

0.18

 Welcome

0.16

 Winner

0.16

meet

0.15

 Award

0.15

urai

0.15

/GPL

0.15

 Based

0.15

When

0.15

Activations Density 0.089%

references to specific locations and events in stories

No Comments

No Known Activations