INDEX

Explanations

statements indicating conditions or requirements in various contexts, especially regarding obligations and responsibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 å¸Ĥ

-0.15

çĦ¶

-0.15

ILLS

-0.15

ARGET

-0.14

utomation

-0.13

 sometimes

-0.13

iddy

-0.13

 ë¶Ļ

-0.13

_CFG

-0.13

errick

-0.13

POSITIVE LOGITS

 soon

0.24

 Soon

0.19

be

0.19

 forthcoming

0.18

Soon

0.18

ingly

0.18

soon

0.17

 future

0.16

å°½

0.15

<[

0.15

Activations Density 1.014%

statements indicating conditions or requirements in various contexts, especially regarding obligations and responsibilities

No Comments

No Known Activations