INDEX

Explanations

references to personal experiences or expressions of individual identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

meg

-0.15

çĻ»

-0.15

oplan

-0.14

ÙĪÙĨØ¯

-0.14

{Name

-0.14

urent

-0.14

=$('#

-0.13

æĿ

-0.13

agate

-0.13

POSITIVE LOGITS

aits

0.16

SENS

0.15

lero

0.14

iag

0.14

ede

0.14

iev

0.14

ousse

0.14

iage

0.14

omanip

0.14

uron

0.14

Activations Density 0.390%

references to personal experiences or expressions of individual identity

No Comments

No Known Activations