INDEX

Explanations

mentions of organization names and partnerships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

veloper

-0.19

ATTER

-0.14

-entry

-0.14

 Ð½Ð°Ð´Ð¾

-0.13

 å£

-0.13

sey

-0.13

ï»¿↵↵

-0.13

 Crown

-0.13

 reportedly

-0.13

ÑħÑĢÐ°Ð½

-0.12

POSITIVE LOGITS

 ourselves

0.30

our

0.29

our

0.22

æĪĳä»¬çļĦ

0.21

 naÅ¡ich

0.18

 nuest

0.17

 Ð½Ð°ÑĪÐ¸Ñħ

0.17

ourd

0.17

 nossa

0.17

 abbiamo

0.16

Activations Density 0.097%

mentions of organization names and partnerships

No Comments

No Known Activations