INDEX

Explanations

mentions of specific plans or structured arrangements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

izado

-0.16

ÑĢÑĥÐ¿

-0.15

ibaba

-0.15

åłĤ

-0.14

å³°

-0.14

ighthouse

-0.14

-light

-0.14

cup

-0.14

eon

-0.14

alli

-0.13

POSITIVE LOGITS

etary

0.31

Ã¨te

0.24

alto

0.20

ets

0.20

ar

0.19

ÐºÑĤ

0.19

eta

0.18

ck

0.18

 Parenthood

0.18

ilha

0.18

Activations Density 0.012%

mentions of specific plans or structured arrangements

No Comments

No Known Activations