INDEX

Explanations

references to individuals involved in documentary projects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

elong

-0.15

agua

-0.15

ìľ¨

-0.15

pector

-0.14

strand

-0.14

Äĥn

-0.14

rud

-0.14

 Ð¿Ð¾Ð¼

-0.14

 å®

-0.13

ervoir

-0.13

POSITIVE LOGITS

 collecting

0.22

 Collect

0.20

 research

0.20

 collected

0.20

 collection

0.20

 recording

0.20

 collect

0.19

 collects

0.18

collect

0.17

 study

0.16

Activations Density 0.085%

references to individuals involved in documentary projects

No Comments

No Known Activations