INDEX

Explanations

references to the year 187 in historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

leta

-0.20

alfa

-0.19

-0.17

 Bout

-0.15

ãĥĥãĤ°

-0.14

reater

-0.14

_inline

-0.14

Ð¾Ð½Ð°

-0.14

 grap

-0.14

Nug

-0.14

POSITIVE LOGITS

achts

0.17

owi

0.16

Luo

0.15

akers

0.15

lies

0.14

shall

0.14

ush

0.14

ig

0.14

ze

0.14

ABCDE

0.14

Activations Density 0.012%

references to the year 187 in historical contexts

No Comments

No Known Activations