INDEX

Explanations

specific terms related to medical conditions and their effects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

cene

-0.17

 deeds

-0.15

bett

-0.15

cia

-0.14

encent

-0.14

Sob

-0.14

acht

-0.14

aris

-0.14

Works

-0.14

oa

-0.14

POSITIVE LOGITS

ailure

0.16

aida

0.15

illard

0.15

halt

0.15

InSection

0.14

å¥

0.14

çı

0.14

.googlecode

0.14

izable

0.14

 Dumpster

0.14

Activations Density 0.075%

specific terms related to medical conditions and their effects

No Comments

No Known Activations