INDEX

Explanations

references to individuals or groups being sent to specific locations or institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

.scalablytyped

-0.16

ìłľ

-0.15

âĢĮ

-0.14

TERN

-0.14

 lesb

-0.14

mani

-0.14

à¹īà¸²à¸ķ

-0.13

æ³ķäºº

-0.13

estr

-0.13

yd

-0.13

POSITIVE LOGITS

aminer

0.16

agara

0.15

tee

0.15

Ú¯Ø±ÛĮ

0.15

orgen

0.14

atsapp

0.14

rome

0.14

endance

0.14

.digital

0.14

egra

0.14

Activations Density 0.027%

references to individuals or groups being sent to specific locations or institutions

No Comments

No Known Activations