INDEX

Explanations

references to data structures or objects in programming languages

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

ãĤ¤ãĤ¯

-0.19

etu

-0.16

 Garland

-0.16

pta

-0.15

ÙĪØ§Ø²

-0.15

è¬Ŀ

-0.15

DebugEnabled

-0.15

Indented

-0.15

regon

-0.15

avax

-0.14

POSITIVE LOGITS

0.16

eda

0.15

istan

0.15

Erd

0.14

 dzieci

0.14

 Loose

0.13

online

0.13

Activations Density 0.215%

references to data structures or objects in programming languages

No Comments

No Known Activations