INDEX

Explanations

terms related to public health and disease analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ÌĨ

-0.16

CLUDED

-0.15

rahim

-0.15

cola

-0.14

ames

-0.14

ÐµÑĩ

-0.14

atorium

-0.14

ç¯

-0.14

á»§

-0.14

asso

-0.14

POSITIVE LOGITS

oa

0.15

ischer

0.15

0.14

AccessException

0.13

 breath

0.13

 Breath

0.13

 pigeon

0.12

ãĥ¼ãĥ«

0.12

 Clayton

0.12

cas

0.12

Activations Density 0.013%

terms related to public health and disease analysis

No Comments

No Known Activations