INDEX

Explanations

references to coats and related items or concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

hoot

-0.20

erator

-0.19

-minded

-0.18

eration

-0.18

erable

-0.16

ously

-0.16

pagesize

-0.16

uder

-0.16

ìĸ¼

-0.15

Soft

-0.15

POSITIVE LOGITS

anic

0.18

ting

0.17

rice

0.16

elry

0.16

ella

0.16

leur

0.15

guns

0.15

ellite

0.15

less

0.15

agini

0.15

Activations Density 0.018%

references to coats and related items or concepts

No Comments

No Known Activations