INDEX

Explanations

references to the Olympics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 impressions

-0.15

Ùĭ

-0.14

aley

-0.14

Äįin

-0.14

clist

-0.14

andler

-0.13

ÑĤÑĮ

-0.13

istry

-0.13

uning

-0.13

gere

-0.13

POSITIVE LOGITS

antity

0.15

amet

0.15

optera

0.15

 Congress

0.14

ngo

0.14

 Kurt

0.14

enor

0.14

crest

0.14

leaflet

0.14

ãĥ¼ãĥ

0.14

Activations Density 0.005%

references to the Olympics

No Comments

No Known Activations