INDEX

Explanations

instances of the word "click" and its variations, indicating calls to action or links to be followed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

hani

-0.15

ÑĢÐ¸Ð½Ð°

-0.14

ximity

-0.14

Py

-0.13

angep

-0.13

pag

-0.13

reste

-0.13

/by

-0.13

mess

-0.13

çŀ

-0.13

POSITIVE LOGITS

 HERE

0.25

ing

0.25

 here

0.25

HERE

0.20

è¿ĻéĩĮ

0.20

_here

0.20

 Here

0.19

 aquÃŃ

0.19

 aqui

0.18

 ÙĩÙĨØ§

0.18

Activations Density 0.010%

instances of the word "click" and its variations, indicating calls to action or links to be followed

No Comments

No Known Activations