INDEX

Explanations

terms related to abstract concepts in programming or class structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

asher

-0.16

izza

-0.15

ij

-0.15

Ã§ak

-0.15

emi

-0.15

olu

-0.14

 Shaft

-0.14

ÅĤo

-0.14

zw

-0.14

IJ

-0.14

POSITIVE LOGITS

ousel

0.15

oyo

0.15

à¸²à¸°

0.15

 addCriterion

0.15

AAD

0.15

ropa

0.15

 è±

0.14

berra

0.14

yk

0.14

 Redistributions

0.14

Activations Density 0.004%

terms related to abstract concepts in programming or class structures

No Comments

No Known Activations