INDEX

Explanations

terms related to location and navigation

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

à¸Ńà¸ĩ

-0.17

uddy

-0.16

æľ

-0.16

-0.15

 stay

-0.15

imo

-0.15

ueva

-0.14

udent

-0.14

reesome

-0.14

POSITIVE LOGITS

antan

0.16

 zurÃ¼ck

0.15

 Ð¿ÑĢÐ¸Ð²ÐµÐ´

0.15

hin

0.15

CRET

0.15

ALER

0.14

etag

0.14

Doe

0.14

 Dess

0.14

igrated

0.14

Activations Density 0.022%

terms related to location and navigation

No Comments

No Known Activations