INDEX

Explanations

numerical data or statistics

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

cent

-0.18

-0.15

asse

-0.15

 ÑĦÐ°ÐºÑĤ

-0.15

Ð»ÑĥÑĪ

-0.14

dec

-0.14

ipi

-0.14

Ã¡r

-0.14

azo

-0.13

ally

-0.13

POSITIVE LOGITS

aland

0.14

acco

0.14

ittel

0.14

_aliases

0.13

Contain

0.13

ILINE

0.13

.Env

0.13

ÑĩÐ°ÑĤ

0.13

indre

0.12

-wall

0.12

Activations Density 0.275%

numerical data or statistics

No Comments

No Known Activations