INDEX

Explanations

references to the White House

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

erea

-0.16

wicklung

-0.15

Â°Ð¡

-0.15

Lng

-0.14

iban

-0.14

 Salt

-0.14

Ð°ÑĢÑĩ

-0.14

dition

-0.14

íĥĿ

-0.13

POSITIVE LOGITS

ocol

0.17

Ð°Ð½Ð¾Ð²

0.15

ÙĨØ§ÙĨ

0.15

Ð¾Ð¼Ð¸Ð½Ð°

0.15

erli

0.14

bek

0.14

 masses

0.14

ÙĥØ§Ùħ

0.14

undles

0.14

bÃŃr

0.14

Activations Density 0.007%

references to the White House

No Comments

No Known Activations

references to the White House

No Comments

No Known Activations