INDEX

Explanations

phrases related to assertions and claims made by individuals or groups

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

subclass

-0.15

onde

-0.15

á»ĩu

-0.15

anke

-0.15

appen

-0.14

oten

-0.14

 Lage

-0.14

á»ĩ

-0.14

appe

-0.13

 Mare

-0.13

POSITIVE LOGITS

 ownership

0.21

 credit

0.20

 jurisdiction

0.20

 expertise

0.19

 having

0.18

 innocence

0.18

 ignorance

0.17

ownership

0.17

nung

0.17

 victory

0.17

Activations Density 0.055%

phrases related to assertions and claims made by individuals or groups

No Comments

No Known Activations