INDEX

Explanations

references to the context of an object or 'this' in programming terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

Ð»Ð¸ÑĪ

-0.17

QualifiedName

-0.15

 Bene

-0.14

_________________↵↵

-0.14

pe

-0.14

ç£¨

-0.14

íĥĿ

-0.14

elder

-0.13

osaurs

-0.13

egers

-0.13

POSITIVE LOGITS

lac

0.17

lobber

0.16

à¸±

0.15

PCS

0.14

VML

0.14

SCII

0.14

 batting

0.14

Å¡t

0.14

adow

0.14

 Sachs

0.14

Activations Density 0.243%

references to the context of an object or 'this' in programming terms

No Comments

No Known Activations