INDEX

Explanations

quotation marks and their context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

ÃŃcul

-0.16

affer

-0.15

SU

-0.15

scratch

-0.15

enler

-0.14

ramid

-0.14

batim

-0.14

suy

-0.14

ataka

-0.13

amient

-0.13

POSITIVE LOGITS

ãĥ¼ãĤ¹ãĥĪ

0.16

och

0.16

ught

0.16

ere

0.15

erring

0.15

asis

0.15

0.14

ãĥ³ãĥ

0.14

Activations Density 0.000%

quotation marks and their context

No Comments

No Known Activations