INDEX

Explanations

patterns related to programming constructs, specifically control flow statements and functions

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

idar

-0.16

hoot

-0.15

alogy

-0.15

vern

-0.14

etri

-0.14

nob

-0.14

edere

-0.14

 Ð´Ð¾Ð´

-0.14

 Cedar

-0.14

/bower

-0.14

POSITIVE LOGITS

onne

0.15

å·¡

0.14

iceps

0.14

bnb

0.14

lla

0.14

jerne

0.14

Äįil

0.14

ieux

0.14

lle

0.14

Ã¡i

0.13

Activations Density 0.062%

patterns related to programming constructs, specifically control flow statements and functions

No Comments

No Known Activations