INDEX

Explanations

prepositions and entities indicating relationships or connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

emon

-0.15

Ol

-0.15

fro

-0.14

 Ston

-0.14

 Arts

-0.14

Fam

-0.14

erm

-0.14

rif

-0.13

leta

-0.13

_PCI

-0.13

POSITIVE LOGITS

neck

0.16

.Generated

0.15

alach

0.15

 ÑĢÐ°Ð·Ð¼

0.14

 ÑĥÑģ

0.14

Ð·Ð¼

0.14

CTL

0.14

å®Ļ

0.14

ByExample

0.14

hx

0.14

Activations Density 0.002%

prepositions and entities indicating relationships or connections

No Comments

No Known Activations