INDEX

Explanations

phrases related to programmatic structures and their effectiveness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

obi

-0.15

perm

-0.14

oundingBox

-0.14

orsk

-0.14

ugs

-0.14

 Holt

-0.14

å¯

-0.14

ocha

-0.14

 Saunders

-0.13

aupt

-0.13

POSITIVE LOGITS

ãĤ¤ãĤº

0.16

ÏĦÏį

0.16

uste

0.15

.nasa

0.15

 prolifer

0.15

isle

0.14

UST

0.14

emmel

0.14

uzu

0.14

Ã¡k

0.13

Activations Density 0.653%

phrases related to programmatic structures and their effectiveness

No Comments

No Known Activations