INDEX

Explanations

references to frequency and severity of events or conditions

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

EMA

-0.15

itler

-0.15

OutOfBoundsException

-0.14

wor

-0.14

abin

-0.14

UNDLE

-0.14

={({

-0.14

ÑĢÐ°ÑģÑĤ

-0.14

reinterpret

-0.14

ESSAGES

-0.14

POSITIVE LOGITS

ions

0.15

ÐµÐ¾

0.15

adows

0.15

ÑĤÐ¸

0.15

ê°ģ

0.14

llum

0.14

arine

0.14

flix

0.14

enth

0.14

atoes

0.13

Activations Density 0.121%

references to frequency and severity of events or conditions

No Comments

No Known Activations