INDEX

Explanations

phrase constructions that involve direct addresses or instructions to the reader

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

\"

-0.14

ryption

-0.14

ÑĢÐ°Ð

-0.14

à¤ªà¤¨

-0.14

sembler

-0.13

.mj

-0.13

.Magenta

-0.13

 sÃłng

-0.13

.Platform

-0.13

tensorflow

-0.13

POSITIVE LOGITS

osate

0.15

0.14

enÃ§Ã£o

0.14

amo

0.13

adays

0.13

/.

0.13

*/),

0.13

 Ãĸr

0.12

atre

0.12

-Cs

0.12

Activations Density 0.464%

phrase constructions that involve direct addresses or instructions to the reader

No Comments

No Known Activations