INDEX

Explanations

references to specific geographical locations, primarily in Alberta and Calgary

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

kiye

-0.17

 adjunct

-0.16

 phen

-0.15

 remot

-0.15

ovÃŃ

-0.14

Īĺ

-0.14

 unto

-0.14

lessly

-0.13

ìļ©

-0.13

rad

-0.13

POSITIVE LOGITS

ades

0.16

istrovstvÃŃ

0.15

à¤¾à¤ĸ

0.15

das

0.15

ovice

0.15

isEmpty

0.14

(Graphics

0.14

 yacc

0.14

asmine

0.14

arkan

0.14

Activations Density 0.005%

references to specific geographical locations, primarily in Alberta and Calgary

No Comments

No Known Activations