INDEX

Explanations

the mention of the term "Dam" and its variations, suggesting a focus on discussions related to dams or similar structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

chaft

-0.16

à¤¾à¤²à¤¯

-0.16

vfs

-0.15

ÐµÐºÑĤÐ¸

-0.15

 åī

-0.15

ernals

-0.15

imler

-0.15

attro

-0.15

iface

-0.14

eil

-0.14

POSITIVE LOGITS

aged

0.22

ned

0.21

Dam

0.21

AGED

0.20

aging

0.19

nable

0.18

dam

0.18

ages

0.18

dam

0.17

mit

0.17

Activations Density 0.012%

the mention of the term "Dam" and its variations, suggesting a focus on discussions related to dams or similar structures

No Comments

No Known Activations