INDEX

Explanations

mentions of instances involving the term "self" in programming or testing contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

lew

-0.15

ErrorHandler

-0.15

 prov

-0.15

Å¯j

-0.14

lfw

-0.14

rente

-0.14

 Went

-0.14

ad

-0.14

 true

-0.14

POSITIVE LOGITS

TPL

0.16

ë¹Ī

0.15

PU

0.15

ï»¿using

0.15

çĽĳåĲ¬é¡µéĿ¢

0.14

Ã§uk

0.14

endcode

0.14

erte

0.14

\grid

0.14

xCB

0.14

Activations Density 0.002%

mentions of instances involving the term "self" in programming or testing contexts

No Comments

No Known Activations