INDEX

Explanations

threats and references to violence or harm

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

gii

-0.18

 Marin

-0.14

Configurer

-0.14

ContentSize

-0.14

ctic

-0.14

crit

-0.14

ilan

-0.13

 Damen

-0.13

bler

-0.13

 Intelligence

-0.13

POSITIVE LOGITS

 targeting

0.17

exter

0.16

Pun

0.16

.dispatchEvent

0.15

StackTrace

0.15

 kill

0.15

owel

0.15

uling

0.14

tribution

0.14

Ð¾Ð¿ÑĢÐ¸

0.14

Activations Density 0.214%

threats and references to violence or harm

No Comments

No Known Activations