INDEX

Explanations

expressions of confusion or discontent regarding expectations and reality

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

avra

-0.15

otal

-0.15

_EXISTS

-0.14

á»ĵi

-0.14

presso

-0.14

kil

-0.14

 Ð¿ÑĢÐ¸Ð´ÐµÑĤÑģÑı

-0.14

Ð°Ð¶

-0.13

tility

-0.13

ront

-0.13

POSITIVE LOGITS

 supposed

1.13

 suppose

0.88

 meant

0.71

 intended

0.52

 supposedly

0.51

 Suppose

0.47

 alleged

0.46

 purported

0.46

SUP

0.46

sup

0.42

Activations Density 0.362%

expressions of confusion or discontent regarding expectations and reality

No Comments

No Known Activations