INDEX

Explanations

terms related to security and safety in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

.eng

-0.15

 Haram

-0.15

ActionCode

-0.15

Ã½v

-0.14

strand

-0.14

evi

-0.14

èĬ¬

-0.14

bourg

-0.14

ogr

-0.14

ãĥ³ãĥĲ

-0.14

POSITIVE LOGITS

mine

0.17

jack

0.16

ably

0.16

 mine

0.15

SOR

0.14

READ

0.14

 Gerr

0.13

ìĦ¤

0.13

go

0.13

flight

0.13

Activations Density 0.015%

terms related to security and safety in various contexts

No Comments

No Known Activations