INDEX

Explanations

instances of the word "visit" and its variations, indicating a focus on visitation or engagement activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

ventus

-0.16

hold

-0.15

vag

-0.15

vice

-0.15

efined

-0.15

enas

-0.14

uida

-0.14

arest

-0.14

hift

-0.14

hots

-0.14

POSITIVE LOGITS

ation

0.27

Scotland

0.23

ations

0.20

ational

0.19

iting

0.18

ting

0.18

ogue

0.17

ng

0.17

ATION

0.17

England

0.17

Activations Density 0.037%

instances of the word "visit" and its variations, indicating a focus on visitation or engagement activities

No Comments

No Known Activations