INDEX

Explanations

phrases indicating conditions or situations that are subject to debate or concern

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

Ì£

-0.16

[email

-0.15

ached

-0.14

iens

-0.14

rim

-0.14

zk

-0.14

 McKenzie

-0.14

paged

-0.14

elsea

-0.14

ongyang

-0.13

POSITIVE LOGITS

 ones

0.17

 backed

0.16

 Brent

0.15

 Wass

0.15

habit

0.14

 ãĦ

0.14

ANCEL

0.14

olf

0.14

/goto

0.14

éĢĶ

0.13

Activations Density 0.108%

phrases indicating conditions or situations that are subject to debate or concern

No Comments

No Known Activations