INDEX

Explanations

connections and relationships between various elements and ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

akers

-0.16

acter

-0.14

inic

-0.14

 Bowie

-0.14

ca

-0.14

sac

-0.14

asto

-0.14

ards

-0.14

ector

-0.13

aker

-0.13

POSITIVE LOGITS

oÄŁ

0.16

enses

0.16

andest

0.15

TEGER

0.15

-scalable

0.14

ëł¨

0.14

ROY

0.14

.way

0.14

.opendaylight

0.14

tk

0.14

Activations Density 0.498%

connections and relationships between various elements and ideas

No Comments

No Known Activations