INDEX

Explanations

negations and expressions of doubt or reluctance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

 currently

-0.22

currently

-0.21

 Currently

-0.19

Currently

-0.19

çĽ®åīį

-0.19

 presently

-0.18

ois

-0.16

Ã¤ge

-0.16

now

-0.16

ijken

-0.15

POSITIVE LOGITS

/is

0.30

 originally

0.30

 Originally

0.23

nt

0.22

 previously

0.22

Originally

0.22

 able

0.20

origin

0.19

abi

0.19

ÑĭÑĪ

0.19

Activations Density 0.052%

negations and expressions of doubt or reluctance

No Comments

No Known Activations