INDEX

Explanations

phrases indicating careful design and formulation of products

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

/cmd

-0.16

-ready

-0.15

wald

-0.13

 Apprent

-0.13

subjects

-0.13

Ready

-0.13

 Ready

-0.13

 Lehr

-0.13

ready

-0.13

POSITIVE LOGITS

hurst

0.16

_Util

0.15

ypad

0.15

agem

0.14

azu

0.14

cono

0.14

ANCES

0.14

Based

0.14

airo

0.14

ÑĩÐ°ÑĤ

0.14

Activations Density 0.114%

phrases indicating careful design and formulation of products

No Comments

No Known Activations