INDEX

Explanations

negations and expressions of denial or contradiction

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

outu

-0.15

irÃ¡

-0.15

acid

-0.14

_utilities

-0.14

rou

-0.14

lab

-0.14

stery

-0.14

arkin

-0.14

Til

-0.14

ady

-0.13

POSITIVE LOGITS

 matter

0.24

 necessarily

0.23

matter

0.21

 matters

0.19

 Matter

0.18

 mattered

0.18

 change

0.17

MAT

0.16

 Matters

0.16

 compares

0.16

Activations Density 0.104%

negations and expressions of denial or contradiction

No Comments

No Known Activations