INDEX

Explanations

phonetic elements and pronunciations in language, particularly focusing on the Swedish language

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

yg

-0.15

arith

-0.15

à¹Ĥà¸ķ

-0.15

syntax

-0.14

.palette

-0.14

nave

-0.14

irim

-0.14

áºŃt

-0.14

æłª

-0.14

language

-0.14

POSITIVE LOGITS

 nasal

0.19

 sound

0.16

 å£°

0.16

à¤¹à¤²

0.15

lide

0.14

 kari

0.14

 open

0.14

ement

0.14

 swallowing

0.14

 voiced

0.14

Activations Density 0.028%

phonetic elements and pronunciations in language, particularly focusing on the Swedish language

No Comments

No Known Activations