INDEX

Explanations

references to processes involving flow, both in physical and metaphorical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ndx

-0.15

phinx

-0.15

ĥĿ

-0.15

 disposal

-0.15

 Competitive

-0.15

SRC

-0.14

 bott

-0.14

_MINOR

-0.14

arkin

-0.14

IRO

-0.14

POSITIVE LOGITS

 signals

0.20

 fluids

0.19

 excess

0.19

ogenerated

0.18

 nutrients

0.17

 fluid

0.17

 waves

0.17

 flows

0.16

 electrons

0.16

æ¬¾

0.16

Activations Density 0.278%

references to processes involving flow, both in physical and metaphorical contexts

No Comments

No Known Activations