INDEX

Explanations

statements about the responsibility for or consequences of actions and decisions

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

 Torrent

-0.15

TO

-0.15

 Mess

-0.15

inia

-0.14

abus

-0.14

akis

-0.14

ekten

-0.14

angl

-0.14

ByExample

-0.13

(æ°´

-0.13

POSITIVE LOGITS

arily

0.18

 ç«ĭ

0.16

Moy

0.15

*)((

0.15

 Balanced

0.15

à¹ĭ

0.14

HTTPHeader

0.14

owie

0.14

 prem

0.14

Activations Density 0.255%

statements about the responsibility for or consequences of actions and decisions

No Comments

No Known Activations