INDEX

Explanations

expressions of appreciation and sentiment towards experiences

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

 ëķĮë¬¸

-0.14

ÑĮÐµ

-0.13

rouch

-0.13

ffff

-0.13

-0.12

ayÄ±m

-0.12

á»¥c

-0.12

umps

-0.12

Ð°ÑĤÐºÑĥ

-0.12

POSITIVE LOGITS

how

1.30

how

1.06

How

0.89

å¦Ĥä½ķ

0.87

HOW

0.86

 cÃ³mo

0.82

-how

0.82

How

0.79

/how

0.74

HOW

0.71

Activations Density 0.676%

expressions of appreciation and sentiment towards experiences

No Comments

No Known Activations