INDEX

Explanations

references to significant individuals and institutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ctal

-0.16

shit

-0.15

earning

-0.14

æľĭ

-0.14

moth

-0.14

 Nachricht

-0.13

 Friendly

-0.13

Ã¤Ã¤

-0.13

.GetItem

-0.13

sah

-0.13

POSITIVE LOGITS

adil

0.18

unft

0.17

/Z

0.16

 ↵↵

0.16

DCF

0.16

Zum

0.15

avel

0.15

frei

0.15

avern

0.14

geist

0.14

Activations Density 0.072%

references to significant individuals and institutions

No Comments

No Known Activations