INDEX

Explanations

words that indicate relationships, support, and assistance within community and collaborative contexts

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

ãĤ¡

-0.17

 Patreon

-0.17

çłĤ

-0.14

Ð»Ð¾Ð¼

-0.14

ãĤ£

-0.14

noc

-0.14

 tinh

-0.14

_iff

-0.14

Linked

-0.13

 è²

-0.13

POSITIVE LOGITS

 conven

0.15

 commercially

0.15

Sie

0.14

ewe

0.14

atter

0.14

ister

0.14

capt

0.14

:o

0.14

 reim

0.14

acular

0.13

Activations Density 0.001%

words that indicate relationships, support, and assistance within community and collaborative contexts

No Comments

No Known Activations