INDEX

Explanations

language related to subtlety and complexity in communication, emphasizing authenticity and avoiding over-simplification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

GX

-0.16

aqu

-0.15

è«

-0.15

ysl

-0.14

Aqu

-0.14

blas

-0.14

hr

-0.14

etik

-0.14

oca

-0.14

oro

-0.14

POSITIVE LOGITS

 ç´

0.17

outers

0.14

 Robot

0.14

avel

0.14

 Masc

0.14

teg

0.14

ILON

0.14

 Spor

0.14

noun

0.14

ledge

0.14

Activations Density 0.322%

language related to subtlety and complexity in communication, emphasizing authenticity and avoiding over-simplification

No Comments

No Known Activations