INDEX

Explanations

keywords related to user-generated content and feedback

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

ixer

-0.16

ondo

-0.15

orsch

-0.15

wares

-0.14

antry

-0.14

ierz

-0.14

ensch

-0.14

onders

-0.14

ields

-0.14

_Val

-0.14

POSITIVE LOGITS

 Hooks

0.16

 Dwight

0.15

ÄŁÄ±nÄ±

0.15

 fatt

0.14

ansa

0.14

empt

0.14

 hook

0.14

 intr

0.14

 hooks

0.14

abase

0.14

Activations Density 0.317%

keywords related to user-generated content and feedback

No Comments

No Known Activations