INDEX

Explanations

references to geographical locations, particularly cities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

anel

-0.17

aget

-0.15

èĭ

-0.15

ntag

-0.15

ÑĪÐ¸Ð²

-0.14

/TT

-0.14

£p

-0.13

 Brendan

-0.13

utdown

-0.13

holds

-0.13

POSITIVE LOGITS

shire

0.17

-average

0.15

ois

0.15

ian

0.15

-based

0.14

ãĤ¯ãĤ»

0.14

gov

0.13

hausen

0.13

Coy

0.13

tec

0.13

Activations Density 0.081%

references to geographical locations, particularly cities

No Comments

No Known Activations