INDEX

Explanations

instances of questioning or inquiry expressions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

æľĭ

-0.16

irsch

-0.15

.googleapis

-0.14

iosis

-0.14

ilo

-0.13

imoto

-0.13

raÃ§

-0.13

rella

-0.13

PACE

-0.13

ACL

-0.13

POSITIVE LOGITS

 OnTrigger

0.15

subclass

0.14

Metrics

0.14

Gut

0.14

ker

0.14

 Metrics

0.14

Ø±ÙĬÙĦ

0.13

 VÅ¡ech

0.13

KER

0.13

/apt

0.13

Activations Density 1.022%

instances of questioning or inquiry expressions

No Comments

No Known Activations