INDEX

Explanations

terms related to expertise or specialized knowledge

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

ankan

-0.16

auses

-0.15

ulu

-0.15

-INF

-0.15

ãĥ¼ãĥŃ

-0.14

ilik

-0.14

Ø°Ùĩ

-0.14

 trai

-0.14

lectric

-0.14

rze

-0.14

POSITIVE LOGITS

ly

0.18

edge

0.17

ise

0.16

 edge

0.15

amat

0.14

 Curtain

0.14

Wyn

0.14

 Edge

0.14

is

0.14

ir

0.14

Activations Density 0.011%

terms related to expertise or specialized knowledge

No Comments

No Known Activations