INDEX

Explanations

metrics related to audience viewership and ratings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

ÂŃn

-0.15

odcast

-0.15

etr

-0.15

errat

-0.15

IRST

-0.14

OWER

-0.14

_NOP

-0.14

alk

-0.14

sed

-0.14

 tele

-0.14

POSITIVE LOGITS

unca

0.17

kowski

0.15

dden

0.14

 Harden

0.14

emek

0.14

uem

0.14

platz

0.14

mia

0.13

BOOLE

0.13

\Migration

0.13

Activations Density 0.050%

metrics related to audience viewership and ratings

No Comments

No Known Activations