INDEX

Explanations

instances of self-identification or declarations of identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

Ä©

-0.14

ÙĨÚ¯ÛĮ

-0.14

rar

-0.14

yny

-0.13

 didSelect

-0.13

 Redistributions

-0.13

bes

-0.13

 Giant

-0.12

orre

-0.12

ListOf

-0.12

POSITIVE LOGITS

ValueChanged

0.14

ipa

0.14

cep

0.14

aty

0.13

aven

0.13

 recep

0.13

EDI

0.13

ones

0.13

ajan

0.13

ulur

0.13

Activations Density 0.071%

instances of self-identification or declarations of identity

No Comments

No Known Activations