INDEX

Explanations

key terms related to vaccination and health policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ischer

-0.19

ilip

-0.16

uhl

-0.15

ATURE

-0.15

uin

-0.15

hf

-0.15

lij

-0.14

Ð§ÐµÑĢ

-0.14

 lá»Ļ

-0.14

ÐĿÐ°Ñģ

-0.14

POSITIVE LOGITS

 Edwards

0.16

dec

0.15

edException

0.15

ascus

0.15

bye

0.15

-ed

0.14

AtA

0.14

ÏĥÏĩ

0.14

edd

0.14

uitka

0.14

Activations Density 0.004%

key terms related to vaccination and health policies

No Comments

No Known Activations