INDEX

Explanations

adverbs that modify verbs or adjectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

-0.17

sto

-0.16

 Ying

-0.14

erialized

-0.14

stime

-0.14

iful

-0.14

uai

-0.14

sted

-0.14

asal

-0.13

ave

-0.13

POSITIVE LOGITS

Ùĩ

0.17

yyyy

0.16

tics

0.16

yyy

0.16

rosse

0.16

gameObject

0.14

apa

0.14

estion

0.14

rics

0.13

referer

0.13

Activations Density 0.631%

adverbs that modify verbs or adjectives

No Comments

No Known Activations