INDEX

Explanations

negative responses or denials

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

itzer

-0.19

/API

-0.17

loth

-0.15

-0.14

idle

-0.14

ulu

-0.14

riter

-0.14

ITO

-0.14

Reviewer

-0.14

API

-0.14

POSITIVE LOGITS

spiel

0.16

apter

0.15

venta

0.15

edList

0.15

ìį¨

0.15

matter

0.14

ãĥĥãĥĪ

0.14

areth

0.14

ool

0.14

ore

0.14

Activations Density 0.096%

negative responses or denials

No Comments

No Known Activations