INDEX

Explanations

connectors and references to various subjects or entities within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

quier

-0.16

allet

-0.14

ÏĥÏĥ

-0.14

 instinct

-0.14

 Contr

-0.14

 circulation

-0.14

ÅĻÃŃzenÃŃ

-0.13

Âľ

-0.13

evin

-0.13

POSITIVE LOGITS

 each

0.18

each

0.18

.each

0.18

 EACH

0.18

æ¯ı

0.16

_each

0.16

 Each

0.16

 chaque

0.16

Each

0.16

 former

0.15

Activations Density 0.003%

connectors and references to various subjects or entities within the text

No Comments

No Known Activations