INDEX

Explanations

references to advertising and commercial aspects of companies, particularly those that utilize new technology or methods

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

ined

-0.17

ÙĨØ¯Ø±

-0.16

ÐĴÑĤ

-0.16

reau

-0.16

-0.15

ossa

-0.15

xia

-0.15

 Shank

-0.15

enco

-0.14

unya

-0.13

POSITIVE LOGITS

Hv

0.15

ONS

0.15

dire

0.14

angler

0.14

 Lambert

0.14

termin

0.14

çľī

0.13

folk

0.13

Optimizer

0.13

åŃĲãģ¯

0.13

Activations Density 0.586%

references to advertising and commercial aspects of companies, particularly those that utilize new technology or methods

No Comments

No Known Activations