INDEX

Explanations

iterating constructs in programming code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

cion

-0.15

emet

-0.14

emem

-0.14

iber

-0.14

MED

-0.14

tip

-0.14

DAC

-0.14

otime

-0.14

ies

-0.13

ha

-0.13

POSITIVE LOGITS

spl

0.18

izedName

0.16

archy

0.16

alloc

0.16

ÑĦÐ¸

0.15

(_,

0.15

 item

0.15

NameValuePair

0.14

Element

0.14

Ä±rak

0.14

Activations Density 0.035%

iterating constructs in programming code

No Comments

No Known Activations