INDEX

Explanations

specific product or brand names within consumer-related contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

oria

-0.17

Ú¯Ø§Ø¨

-0.16

å¯

-0.16

egt

-0.16

orias

-0.15

Î¼Î¯

-0.15

VISIBLE

-0.15

ahir

-0.15

ÑĨÐ¾Ð²

-0.15

oga

-0.14

POSITIVE LOGITS

 shooters

0.25

 shooting

0.24

 Nikon

0.23

 shooter

0.23

 autofocus

0.22

 mount

0.22

 lens

0.21

 rang

0.21

 Bayer

0.21

 port

0.21

Activations Density 0.027%

specific product or brand names within consumer-related contexts

No Comments

No Known Activations