INDEX

Explanations

discussions about language pronunciation and characteristics

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

çĨ

-0.16

&o

-0.15

phan

-0.15

.refs

-0.15

 ArrayBuffer

-0.14

oref

-0.14

hatt

-0.14

oner

-0.14

anth

-0.14

Ð¿Ð¾Ð²

-0.13

POSITIVE LOGITS

 sounds

0.22

 silent

0.19

silent

0.19

 sound

0.19

 Silent

0.18

 conson

0.18

ough

0.18

 sounded

0.18

 Sounds

0.18

sounds

0.18

Activations Density 0.037%

discussions about language pronunciation and characteristics

No Known Activations