INDEX

Explanations

occurrences of the word "Ein" and its variations in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ks

-0.15

ulk

-0.15

abel

-0.14

à¸´à¸Ķà¸Ĥ

-0.14

á»įt

-0.14

childNodes

-0.14

antly

-0.14

Daw

-0.14

yms

-0.14

ille

-0.13

POSITIVE LOGITS

akter

0.17

agini

0.16

hell

0.16

richt

0.16

zel

0.16

zelf

0.15

iges

0.15

Ø§Ùĩ

0.14

Lod

0.14

ãĤ¤ãĥĦ

0.14

Activations Density 0.007%

occurrences of the word "Ein" and its variations in different contexts

No Comments

No Known Activations