INDEX

Explanations

punctuation marks and their patterns in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

Ð¾Ñĩ

-0.14

 Malk

-0.14

itude

-0.14

--

-0.14

 Ð½Ð°Ð´Ð¾

-0.13

 conson

-0.13

elve

-0.13

MESS

-0.13

é

-0.13

 molec

-0.13

POSITIVE LOGITS

Å¼e

0.15

ESH

0.15

tej

0.15

Lets

0.14

orden

0.14

frauen

0.14

ena

0.14

 Lets

0.14

Attached

0.13

 ëĺĲíķľ

0.13

Activations Density 0.753%

punctuation marks and their patterns in sentences

No Comments

No Known Activations