INDEX

Explanations

SQL commands and database schema manipulation terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

Assignable

-0.17

StateChanged

-0.16

 ÐĹÐ°Ð³

-0.15

rist

-0.15

ilo

-0.14

tern

-0.14

tract

-0.14

tro

-0.14

borg

-0.14

xaa

-0.14

POSITIVE LOGITS

inker

0.18

inine

0.17

/Delete

0.15

á»ĭch

0.15

_exempt

0.15

inus

0.15

endir

0.14

orida

0.14

ktion

0.14

 hete

0.14

Activations Density 0.030%

SQL commands and database schema manipulation terms

No Comments

No Known Activations