INDEX

Explanations

patterns of expressions or opinions related to experiences and emotions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

ableObject

-0.14

 numberWith

-0.13

_buff

-0.13

\Collections

-0.13

ces

-0.13

UITableViewCell

-0.13

/class

-0.12

ffd

-0.12

psilon

-0.12

Ã½v

-0.12

POSITIVE LOGITS

enda

0.16

á»¥n

0.14

ãĥ¼ãĥ©

0.13

 lever

0.13

 Belt

0.13

-overlay

0.13

acha

0.13

\xf

0.12

ãĥ¼ãĥĵ

0.12

Activations Density 0.486%

patterns of expressions or opinions related to experiences and emotions

No Comments

No Known Activations