INDEX

Explanations

references to ecological topics and natural environments

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

 Antarctic

-0.18

 Alpine

-0.17

 Boise

-0.15

 Antarctica

-0.15

Tas

-0.15

 Boulder

-0.15

Seattle

-0.15

 Desert

-0.15

#.

-0.14

 bushes

-0.14

POSITIVE LOGITS

 Carolina

0.22

Oz

0.22

pec

0.21

 Hick

0.21

 knobs

0.21

Yad

0.21

Cah

0.20

tup

0.20

 Cherokee

0.19

Yaz

0.19

Activations Density 0.175%

references to ecological topics and natural environments

No Comments

No Known Activations