INDEX

Explanations

indicators of publication and reference details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Ã¡la

-0.15

Te

-0.15

RAFT

-0.14

Teh

-0.14

atches

-0.14

OTA

-0.13

raft

-0.13

rose

-0.13

band

-0.13

POSITIVE LOGITS

ADDE

0.17

.screen

0.17

ToFront

0.16

 serialVersionUID

0.16

.Spring

0.15

çģµ

0.15

trer

0.14

ijn

0.14

ewan

0.14

eydi

0.14

Activations Density 0.071%

indicators of publication and reference details

No Comments

No Known Activations