INDEX

Explanations

terms related to geometry, specifically concerning concave and convex shapes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

phan

-0.17

ãĤ¤ãĤ¯

-0.17

-0.15

Î¸Î·

-0.14

iego

-0.14

à¤¿à¤¥

-0.14

ntl

-0.14

 wing

-0.14

Ñŀ

-0.14

gram

-0.14

POSITIVE LOGITS

CHAT

0.16

ric

0.14

 leadership

0.14

ajas

0.14

asser

0.14

Jos

0.14

 Hull

0.14

rise

0.14

ypy

0.13

ETY

0.13

Activations Density 0.005%

terms related to geometry, specifically concerning concave and convex shapes

No Comments

No Known Activations