INDEX

Explanations

patterns or sequences involving the "N/A" notation, likely related to data entries or coding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

emez

-0.16

-0.15

pone

-0.15

ULD

-0.14

lia

-0.14

AdapterFactory

-0.14

 Hanging

-0.14

auer

-0.14

formance

-0.14

za

-0.14

POSITIVE LOGITS

adera

0.15

Fel

0.15

initWith

0.15

-describedby

0.15

ìĬ¤

0.14

ipel

0.14

eczy

0.14

êµ°

0.14

 åįĬ

0.14

ichel

0.13

Activations Density 0.034%

patterns or sequences involving the "N/A" notation, likely related to data entries or coding

No Comments

No Known Activations