INDEX

Explanations

references to specific products or agreements within community or organizational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

atte

-0.15

ŀ

-0.15

ì§ĢëıĦ

-0.15

asel

-0.15

 Primitive

-0.14

interest

-0.14

 celib

-0.14

atter

-0.14

.partial

-0.14

paj

-0.13

POSITIVE LOGITS

arkan

0.16

bles

0.15

Lem

0.15

ÃŃtica

0.15

 Coul

0.15

-INF

0.15

mey

0.15

ahoo

0.15

polator

0.14

DataExchange

0.14

Activations Density 0.018%

references to specific products or agreements within community or organizational contexts

No Comments

No Known Activations