INDEX

Explanations

references to character relationships and emotional struggles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

ult

-0.15

ican

-0.14

olds

-0.14

 stops

-0.13

ita

-0.13

ij

-0.13

ovi

-0.13

à¸Ńà¸Ļà¸Ĺ

-0.13

estro

-0.13

 IDENT

-0.13

POSITIVE LOGITS

 plunged

0.29

 entered

0.28

-enter

0.28

 entering

0.26

 enters

0.26

è¿Ľåħ¥

0.25

 Entered

0.25

 thrust

0.25

 enter

0.24

Entering

0.24

Activations Density 0.145%

references to character relationships and emotional struggles

No Comments

No Known Activations