INDEX

Explanations

verbs and actions related to reporting and presenting information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

osu

-0.17

endi

-0.17

ermen

-0.15

.toolbox

-0.15

aleza

-0.14

erm

-0.14

ONEY

-0.14

oney

-0.14

 ç«

-0.13

POSITIVE LOGITS

via

0.18

via

0.16

incinn

0.15

abis

0.15

pai

0.14

 either

0.14

 correspond

0.14

aspers

0.14

commons

0.14

Via

0.14

Activations Density 0.005%

verbs and actions related to reporting and presenting information

No Comments

No Known Activations