INDEX

Explanations

punctuation and symbols used in programming or markup languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ustum

-0.17

æĳĺ

-0.16

warts

-0.16

 ÐĴÐ¸ÐºÐ¸

-0.15

ech

-0.15

oir

-0.15

hea

-0.14

achi

-0.14

ONG

-0.14

owards

-0.14

POSITIVE LOGITS

pard

0.17

ory

0.15

ty

0.15

PTH

0.14

pec

0.14

 Happy

0.14

 Pascal

0.14

peq

0.14

zos

0.14

ologist

0.14

Activations Density 0.115%

punctuation and symbols used in programming or markup languages

No Comments

No Known Activations