INDEX

Explanations

terms related to patronage and support

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ern

-0.17

een

-0.17

ÑĥÐ¹

-0.15

onth

-0.14

enda

-0.14

.AddListener

-0.14

led

-0.14

clipse

-0.14

irement

-0.14

ibe

-0.14

POSITIVE LOGITS

OI

0.19

prung

0.16

?type

0.15

.ly

0.15

izes

0.14

.Safe

0.14

æµ©

0.14

alama

0.14

 Telecom

0.13

loha

0.13

Activations Density 0.005%

terms related to patronage and support

No Comments

No Known Activations