INDEX

Explanations

terms related to audience and readership engagement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ãĥ¼ãĤ¯

-0.16

mlink

-0.16

ë¥ĺ

-0.15

Hosting

-0.14

ighton

-0.14

enda

-0.14

Cyr

-0.14

flu

-0.14

oken

-0.14

wm

-0.14

POSITIVE LOGITS

/view

0.20

/client

0.19

/read

0.17

/list

0.17

hip

0.16

atik

0.16

/Users

0.16

/watch

0.15

/custom

0.15

alley

0.15

Activations Density 0.120%

terms related to audience and readership engagement

No Comments

No Known Activations