INDEX

Explanations

geographical locations and names associated with specific places

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

illon

-0.15

ople

-0.15

irut

-0.14

lal

-0.14

amel

-0.14

rement

-0.14

atum

-0.13

elta

-0.13

ÏĬ

-0.13

piler

-0.13

POSITIVE LOGITS

halt

0.16

oslav

0.16

/py

0.14

osate

0.14

íĥĦ

0.14

ë²Į

0.14

 partially

0.14

rrha

0.14

ÅŁÄ±

0.14

erdale

0.14

Activations Density 0.076%

geographical locations and names associated with specific places

No Comments

No Known Activations