INDEX

Explanations

intensifiers that express strong emotions or sentiments

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

ighth

-0.15

orio

-0.15

lop

-0.14

pery

-0.14

sure

-0.14

aos

-0.14

|[

-0.14

unky

-0.13

itta

-0.13

&action

-0.13

POSITIVE LOGITS

oper

0.20

 glad

0.18

so

0.18

-so

0.17

oo

0.16

OMPI

0.16

OPER

0.16

Ð»ÐµÐ¹

0.15

unds

0.15

aks

0.15

Activations Density 0.056%

intensifiers that express strong emotions or sentiments

No Comments

No Known Activations