INDEX

Explanations

method calls related to data retrieval and manipulation

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

Î³Îº

-0.13

 Madness

-0.13

arel

-0.13

van

-0.13

vak

-0.12

/Error

-0.12

hai

-0.12

Ð²ÐµÑģÑĤ

-0.12

hc

-0.12

áº»

-0.12

POSITIVE LOGITS

activex

0.15

 konkrÃ©t

0.15

ataka

0.15

ewe

0.14

Active

0.14

ãĥ³ãĥĩãĤ£

0.14

iT

0.13

 ActiveForm

0.13

BUM

0.13

iesen

0.13

Activations Density 0.011%

method calls related to data retrieval and manipulation

No Comments

No Known Activations