INDEX

Explanations

the presence of specific phonetic patterns or sequences in words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

kaÃ§

-0.15

chooser

-0.15

ÄĻÅ¼

-0.14

uela

-0.14

atype

-0.14

itre

-0.14

liÅ¡

-0.14

rani

-0.14

losures

-0.13

webtoken

-0.13

POSITIVE LOGITS

edList

0.14

arpa

0.14

ACTER

0.13

ffer

0.13

 dear

0.13

oire

0.13

standing

0.13

ë³µ

0.13

edian

0.13

 standing

0.13

Activations Density 0.295%

the presence of specific phonetic patterns or sequences in words

No Comments

No Known Activations