INDEX

Explanations

references to a specific type of pentagon or pentagonal structure

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aged

-0.15

vard

-0.15

ins

-0.15

kus

-0.15

sp

-0.15

 Wolf

-0.14

 Grant

-0.14

od

-0.14

yet

-0.14

POSITIVE LOGITS

ekim

0.16

mtime

0.15

ahun

0.15

ãĥŃãĥ¼

0.15

 addCriterion

0.14

Éµ

0.14

ModelProperty

0.14

etr

0.14

egend

0.14

egov

0.14

Activations Density 0.009%

references to a specific type of pentagon or pentagonal structure

No Comments

No Known Activations