INDEX

Explanations

references to "mass" in various contexts, often related to mass media or mass production

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

eyn

-0.16

ÑģÑĤÐ°ÑĤÐ¸

-0.15

eko

-0.15

orns

-0.14

jun

-0.14

/manage

-0.14

 bufsize

-0.14

 Aires

-0.14

isms

-0.14

pty

-0.13

POSITIVE LOGITS

achusetts

0.35

ively

0.28

aging

0.27

acre

0.26

iveness

0.26

imo

0.25

achuset

0.24

ive

0.24

ses

0.23

 mass

0.23

Activations Density 0.026%

references to "mass" in various contexts, often related to mass media or mass production

No Comments

No Known Activations