INDEX

Explanations

specific scientific or technical terms and their relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

oron

-0.16

yah

-0.16

Haj

-0.15

tok

-0.15

.tt

-0.14

sap

-0.14

kili

-0.14

[ii

-0.14

athers

-0.14

çĴ

-0.14

POSITIVE LOGITS

 Bilg

0.16

eci

0.15

iani

0.14

aminer

0.14

axy

0.14

oci

0.14

utos

0.13

pite

0.13

 Calder

0.13

ount

0.13

Activations Density 0.012%

specific scientific or technical terms and their relationships

No Comments

No Known Activations