INDEX

Explanations

references to numerical years, particularly those in the 1800s

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

sch

-0.16

ulas

-0.16

ering

-0.16

adius

-0.15

space

-0.15

ammers

-0.14

ateau

-0.14

 HÃ¼s

-0.14

erate

-0.14

Lub

-0.14

POSITIVE LOGITS

 CONSEQUENTIAL

0.15

Ð»ÐµÐºÑģ

0.15

ÑĤÐ¸

0.15

ised

0.15

ÑĤÐ¾ÑĢ

0.14

AGED

0.14

oq

0.14

LOAT

0.14

ining

0.14

Activations Density 0.014%

references to numerical years, particularly those in the 1800s

No Comments

No Known Activations