INDEX

Explanations

instances of significant events or milestones

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

ħn

-0.15

 proport

-0.15

urch

-0.14

lÃ©m

-0.14

PCS

-0.14

zet

-0.14

ANEL

-0.14

Uhr

-0.14

illac

-0.14

 MethodInfo

-0.14

POSITIVE LOGITS

ovit

0.16

eks

0.15

 spin

0.15

 nice

0.14

lid

0.14

gan

0.13

rej

0.13

ulas

0.13

ike

0.13

lace

0.13

Activations Density 0.000%

instances of significant events or milestones

No Comments

No Known Activations