INDEX

Explanations

phrases questioning differences or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ront

-0.17

tron

-0.16

 mouths

-0.16

lier

-0.15

 mouth

-0.14

ulk

-0.14

 majority

-0.14

okoj

-0.13

iej

-0.13

older

-0.13

POSITIVE LOGITS

 difference

0.20

 purpose

0.18

Purpose

0.18

 Difference

0.17

purpose

0.17

difference

0.17

 Purpose

0.17

urpose

0.16

ilden

0.15

 meaning

0.15

Activations Density 0.044%

phrases questioning differences or comparisons

No Comments

No Known Activations