INDEX

Explanations

information related to victory and success in competitive contexts

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

åľ¨

-0.18

Ã½n

-0.17

bote

-0.16

ç«Ļåľ¨

-0.16

æĶ¾åľ¨

-0.16

Ø±Ø§

-0.15

GenerationStrategy

-0.15

oner

-0.15

regor

-0.15

ÑĶÐ¼

-0.15

POSITIVE LOGITS

 guise

0.28

 ÙĪÙģÙĬ

0.25

 fashion

0.25

 manner

0.25

 context

0.25

 sense

0.24

 format

0.21

 midst

0.21

 terms

0.20

 meantime

0.20

Activations Density 2.280%

information related to victory and success in competitive contexts

No Comments

No Known Activations