INDEX

Explanations

numerical addresses or identifiers, particularly in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ong

-0.16

à¸ĩ

-0.16

mons

-0.15

uce

-0.15

eros

-0.15

lez

-0.15

angs

-0.14

 Alley

-0.14

gable

-0.14

uxtap

-0.14

POSITIVE LOGITS

ties

0.19

UILD

0.16

icina

0.16

à¤¿à¤£

0.15

eur

0.15

rez

0.15

]={↵

0.15

ti

0.15

sburg

0.15

tier

0.15

Activations Density 0.053%

numerical addresses or identifiers, particularly in a structured format

No Comments

No Known Activations