INDEX

Explanations

references to competitions and awards

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ilim

-0.15

hey

-0.15

ogany

-0.14

pedia

-0.14

agens

-0.14

alink

-0.14

iani

-0.13

Î³Î¿Î½

-0.13

cctor

-0.13

 REFER

-0.13

POSITIVE LOGITS

 winner

0.28

 winners

0.28

 selected

0.26

winner

0.23

selected

0.23

 chosen

0.22

 select

0.22

 selects

0.21

 winning

0.21

 vict

0.21

Activations Density 0.092%

references to competitions and awards

No Comments

No Known Activations