INDEX

Explanations

social interactions and relationships

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

±

-0.17

ÌĨ

-0.16

ENSE

-0.15

.gt

-0.14

ngth

-0.14

okrat

-0.14

CodeAt

-0.13

uiltin

-0.13

Ø¬Ø©

-0.13

uth

-0.13

POSITIVE LOGITS

 yard

0.17

 whom

0.15

_DAT

0.15

 shame

0.15

 Shame

0.14

essler

0.14

INVAL

0.14

 Yard

0.14

 lack

0.13

Ã¡vÄĽ

0.13

Activations Density 0.125%

social interactions and relationships

No Comments

No Known Activations