INDEX

Explanations

references to trails and pathways in natural settings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 hills

-0.17

vit

-0.16

 Hills

-0.15

lac

-0.15

 highways

-0.15

 mountains

-0.14

 Darkness

-0.14

 exped

-0.14

 downtown

-0.14

 routes

-0.13

POSITIVE LOGITS

 signed

0.19

signed

0.19

 faint

0.17

ury

0.17

 scram

0.17

 unsigned

0.16

bench

0.16

unsigned

0.15

 switch

0.15

 gint

0.15

Activations Density 0.005%

references to trails and pathways in natural settings

No Comments

No Known Activations