INDEX

Explanations

instances of the word "ruin" and its variations, particularly in contexts related to life or reputation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ki

-0.15

 ÑģÑĤÐ°Ð½

-0.15

illez

-0.14

.faces

-0.14

gia

-0.14

èį

-0.14

airo

-0.13

 Â©

-0.13

AndPassword

-0.13

POSITIVE LOGITS

«a

0.17

æİī

0.16

icio

0.15

ously

0.15

aken

0.14

oltage

0.14

igital

0.14

ensburg

0.14

ably

0.14

exus

0.14

Activations Density 0.034%

instances of the word "ruin" and its variations, particularly in contexts related to life or reputation

No Comments

No Known Activations