INDEX

Explanations

references to locations and names associated with addresses or places in Canada

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

-0.17

 Torres

-0.15

ifik

-0.15

erties

-0.15

mast

-0.14

_specs

-0.14

ãĥĩãĤ£ãĤ¢

-0.14

 Levin

-0.14

specs

-0.14

 Lopez

-0.14

POSITIVE LOGITS

anych

0.18

 Siemens

0.17

 Cardinal

0.17

ighet

0.17

 Trem

0.17

osit

0.17

 Parad

0.15

Mac

0.15

inning

0.15

 Forget

0.15

Activations Density 0.069%

references to locations and names associated with addresses or places in Canada

No Comments

No Known Activations