INDEX

Explanations

terminology related to cellular structures or types

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

portun

-0.17

iode

-0.17

ymb

-0.16

hind

-0.15

ftime

-0.14

ipp

-0.14

amil

-0.14

nem

-0.14

Ð»ÐµÐº

-0.14

elerik

-0.14

POSITIVE LOGITS

ãĥĥãĤ·ãĥ¥

0.16

 Everest

0.16

 Svens

0.15

Î¯Î´

0.15

/svg

0.14

à¸«à¸Ļ

0.14

ÃŃm

0.14

Ã¡ty

0.14

orrh

0.14

ÃŃÅ¾

0.13

Activations Density 0.008%

terminology related to cellular structures or types

No Known Activations