INDEX

Explanations

words and phrases related to existence and its classifications

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

Not in Any Lists

No Comments

Negative Logits

eag

-0.14

 Newman

-0.14

ë©

-0.13

é¾Ħ

-0.13

loud

-0.13

ichick

-0.13

å¸¯

-0.13

¼

-0.13

Har

-0.13

ÑĪÑĤ

-0.13

POSITIVE LOGITS

ent

0.68

ents

0.65

ENT

0.56

ently

0.55

ente

0.52

enti

0.51

ÐµÐ½ÑĤ

0.51

ency

0.50

entes

0.48

ence

0.46

Activations Density 0.108%

words and phrases related to existence and its classifications

No Comments

No Known Activations