INDEX

Explanations

specific patterns or syntax in programming code, particularly focusing on function definitions and manipulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

amo

-0.17

isos

-0.17

vre

-0.16

}}],↵

-0.16

iso

-0.16

SEL

-0.15

isoft

-0.15

esh

-0.14

_beam

-0.14

unt

-0.14

POSITIVE LOGITS

 åĽ

0.15

undle

0.15

echa

0.14

ekim

0.14

 conceptual

0.14

 personnel

0.14

rous

0.14

enta

0.14

undles

0.14

if

0.14

Activations Density 0.070%

specific patterns or syntax in programming code, particularly focusing on function definitions and manipulations

No Comments

No Known Activations