INDEX

Explanations

programming constructs related to object management and function definitions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

aign

-0.15

lected

-0.15

åħ½

-0.14

ç®±

-0.14

ÏĩÎ±Î½

-0.14

kovÄĽ

-0.13

ÑĨÐ¾

-0.13

Ã¼rn

-0.13

 PureComponent

-0.13

ictionary

-0.13

POSITIVE LOGITS

æľīéĻĲ

0.15

 Grip

0.14

ple

0.14

ÑĢÐ¸Ð·

0.14

 yourselves

0.14

 Incontri

0.13

 Parallel

0.13

ersed

0.13

adamente

0.13

ëĭ¤ìļ´

0.13

Activations Density 0.413%

programming constructs related to object management and function definitions

No Comments

No Known Activations