INDEX

Explanations

phrases indicating intense emotions or experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ncia

-0.15

 subs

-0.15

icap

-0.14

reau

-0.14

ydro

-0.14

Å¯r

-0.14

tha

-0.14

tn

-0.14

 klik

-0.14

roys

-0.14

POSITIVE LOGITS

ucci

0.17

apol

0.16

à¹Īà¸Ńà¸ĩ

0.15

iosk

0.15

bdd

0.14

Ð²Ð°ÑĤ

0.14

nod

0.14

ernet

0.14

ERR

0.14

lij

0.14

Activations Density 0.000%

phrases indicating intense emotions or experiences

No Comments

No Known Activations