INDEX

Explanations

terms related to prominent figures or key concepts in a text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

atro

-0.15

HAR

-0.14

argas

-0.14

askell

-0.14

ovit

-0.14

Ã´ng

-0.14

forces

-0.14

erge

-0.14

nell

-0.13

::↵

-0.13

POSITIVE LOGITS

ä¼ı

0.17

TEE

0.17

ANGO

0.16

shima

0.15

inations

0.15

 Pere

0.14

å±Ĭ

0.14

tainment

0.14

UDO

0.14

.flink

0.14

Activations Density 0.002%

terms related to prominent figures or key concepts in a text

No Comments

No Known Activations