INDEX

Explanations

German words indicating actions and descriptions, particularly those related to human behavior and circumstances

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

ettel

-0.20

uite

-0.16

 Richardson

-0.15

azer

-0.15

abus

-0.15

ÐµÐ·Ð´

-0.14

jd

-0.14

icher

-0.14

lass

-0.14

dna

-0.14

POSITIVE LOGITS

iert

0.26

agt

0.25

elt

0.25

gt

0.25

Ð°ÐµÑĤ

0.24

igt

0.24

ibt

0.23

ÑĢÑĥÐµÑĤ

0.23

ÑĥÑĶ

0.23

ÑĭÐ²Ð°ÐµÑĤ

0.23

Activations Density 0.034%

German words indicating actions and descriptions, particularly those related to human behavior and circumstances

No Comments

No Known Activations