INDEX

Explanations

references to individuals or entities that have the title "Tat" or variations of it

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

iÄĻ

-0.17

etas

-0.16

clas

-0.16

byname

-0.15

irie

-0.15

å®ľ

-0.14

eller

-0.14

Ð¾Ð´Ð°Ð²

-0.14

orr

-0.14

.advance

-0.14

POSITIVE LOGITS

iana

0.24

oo

0.20

too

0.18

oose

0.16

heimer

0.16

anka

0.15

tool

0.15

oueur

0.15

vern

0.15

elman

0.15

Activations Density 0.011%

references to individuals or entities that have the title "Tat" or variations of it

No Comments

No Known Activations