INDEX

Explanations

phrases indicating existence or identity in a variety of contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

gee

-0.17

 poste

-0.15

universal

-0.15

 Reaper

-0.15

 universal

-0.15

ekim

-0.15

onal

-0.14

thinkable

-0.14

asd

-0.14

oller

-0.14

POSITIVE LOGITS

affer

0.17

adder

0.17

azar

0.16

iser

0.15

Ãµi

0.15

 Rupert

0.15

kol

0.15

mitter

0.14

azu

0.14

 station

0.14

Activations Density 0.020%

phrases indicating existence or identity in a variety of contexts

No Comments

No Known Activations