INDEX

Explanations

elements and attributes within code or markup structure

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

ain

-0.18

ings

-0.17

-0.16

most

-0.16

-0.15

ypad

-0.15

ler

-0.15

ative

-0.15

POSITIVE LOGITS

ehir

0.15

Î»ÎµÎº

0.15

imdi

0.14

hue

0.14

eydi

0.14

ÐµÑı

0.13

ewis

0.13

Interop

0.13

.hm

0.13

Activations Density 0.255%

elements and attributes within code or markup structure

No Comments

No Known Activations