INDEX

Explanations

phrases indicating the validation and failure of resource and user policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 (*((

-0.16

alse

-0.15

DebugEnabled

-0.15

ibu

-0.15

ibre

-0.15

anz

-0.14

 formation

-0.14

andr

-0.14

ÅĻel

-0.14

emics

-0.14

POSITIVE LOGITS

 Stan

0.18

 ÙħØ²

0.15

ç¥¥

0.14

urd

0.14

Stan

0.14

jab

0.14

aska

0.14

liness

0.14

 stan

0.14

stra

0.14

Activations Density 0.022%

phrases indicating the validation and failure of resource and user policies

No Comments

No Known Activations