INDEX

Explanations

present tense forms of the verb "to be" and related words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

 lÃ²ng

-0.16

alo

-0.16

icz

-0.15

esson

-0.15

enÃ§a

-0.15

occo

-0.15

alent

-0.14

 CLICK

-0.14

spot

-0.14

POSITIVE LOGITS

mesh

0.25

 masse

0.21

listing

0.19

erv

0.18

eb

0.17

shr

0.17

fold

0.17

unciation

0.17

ibri

0.17

oug

0.16

Activations Density 0.017%

present tense forms of the verb "to be" and related words

No Comments

No Known Activations