INDEX

Explanations

historical events and significant dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 deltaX

-0.14

ite

-0.14

rete

-0.14

åīĤ

-0.13

oot

-0.13

suite

-0.13

ereo

-0.13

 suit

-0.13

ABB

-0.13

tring

-0.13

POSITIVE LOGITS

dash

0.18

raquo

0.17

emics

0.14

emoc

0.14

 smoothed

0.14

SEL

0.13

PSA

0.13

para

0.13

 Ð¼Ð°Ð·

0.13

Activations Density 0.074%

historical events and significant dates

No Comments

No Known Activations