INDEX

Explanations

negations and expressions of doubt or uncertainty

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

arp

-0.15

amo

-0.15

 withdraw

-0.14

outu

-0.14

ories

-0.14

ues

-0.14

inar

-0.14

hatt

-0.14

acid

-0.13

ary

-0.13

POSITIVE LOGITS

 necessarily

0.28

 matter

0.22

matter

0.20

 mattered

0.19

 ever

0.17

ecessarily

0.17

 matters

0.16

 Matter

0.16

 compares

0.16

ylland

0.16

Activations Density 0.125%

negations and expressions of doubt or uncertainty

No Comments

No Known Activations