INDEX

Explanations

references to mental states or psychological conditions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

gis

-0.15

 stiff

-0.15

 discomfort

-0.15

urv

-0.14

nesty

-0.14

GIS

-0.14

 dolor

-0.14

 sting

-0.14

ustom

-0.14

ibble

-0.14

POSITIVE LOGITS

 insanity

0.49

 madness

0.48

 insane

0.45

 crazy

0.45

lun

0.45

mad

0.44

mad

0.43

 craz

0.42

 Crazy

0.42

 sanity

0.40

Activations Density 0.397%

references to mental states or psychological conditions

No Comments

No Known Activations