INDEX

Explanations

references to programming concepts and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

-0.16

 Burb

-0.16

ense

-0.16

ed

-0.15

enda

-0.15

_mut

-0.15

al

-0.15

ving

-0.14

 Gregg

-0.14

Ta

-0.14

POSITIVE LOGITS

oÅ¾

0.16

patches

0.15

 VÅ¡ech

0.15

sher

0.15

áº«

0.15

.statusText

0.14

__);

0.14

 Luna

0.14

usercontent

0.14

HttpException

0.14

Activations Density 0.115%

references to programming concepts and structures

No Comments

No Known Activations