INDEX

Explanations

dates and references to specific time periods

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

ç«ĭãģ¦

-0.18

Ã©m

-0.17

æĮ¯ãĤĬ

-0.16

ajs

-0.15

FullYear

-0.15

 Ð½Ð°ÑĤÑĥ

-0.14

eca

-0.14

chter

-0.14

:numel

-0.14

POSITIVE LOGITS

 currently

0.14

 presently

0.14

 fitte

0.14

vore

0.14

tery

0.13

 spons

0.13

 Gardens

0.13

qml

0.13

ãĥ¼ãĥĸãĥ«

0.13

 Movement

0.13

Activations Density 0.204%

dates and references to specific time periods

No Comments

No Known Activations