INDEX

Explanations

terms related to anthropology and its various sub-disciplines

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

istani

-0.18

Ð´Ð¸Ñı

-0.18

yw

-0.17

erland

-0.15

iture

-0.15

yk

-0.15

ç°

-0.15

.nih

-0.14

unfold

-0.14

ythe

-0.14

POSITIVE LOGITS

omorphic

0.23

 Anth

0.23

 anth

0.22

anth

0.20

ause

0.20

Anth

0.18

ology

0.18

logy

0.17

oney

0.16

ological

0.16

Activations Density 0.009%

terms related to anthropology and its various sub-disciplines

No Comments

No Known Activations