INDEX

Explanations

phrases indicating geographic locations or descriptions related to being in a centralized or isolated position

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

cin

-0.16

ving

-0.15

 PROT

-0.15

Ð°ÑĢÐ¾Ð²

-0.15

ynth

-0.14

HttpStatus

-0.14

atik

-0.14

nek

-0.14

 ÏĢÏģÏĮ

-0.14

antu

-0.13

POSITIVE LOGITS

 nowhere

0.42

/end

0.19

åĬ

0.17

 ongoing

0.17

 otherwise

0.16

 confusion

0.16

/right

0.16

º

0.16

-action

0.15

otherwise

0.15

Activations Density 0.038%

phrases indicating geographic locations or descriptions related to being in a centralized or isolated position

No Comments

No Known Activations