INDEX

Explanations

the word "rather" indicating preferences or alternatives in various contexts

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

ridge

-0.19

ahl

-0.17

irit

-0.15

acon

-0.15

acia

-0.14

’te

-0.14

exion

-0.14

Buffers

-0.14

amura

-0.14

Ãºi

-0.13

POSITIVE LOGITS

 than

0.37

than

0.26

 THAN

0.21

_than

0.20

 niÅ¼

0.19

-than

0.18

 Than

0.18

 Ã¤n

0.17

Than

0.17

 neÅ¾

0.17

Activations Density 0.016%

the word "rather" indicating preferences or alternatives in various contexts

No Comments

No Known Activations