INDEX

Explanations

information related to podcasts or radio shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

endars

-0.16

urat

-0.15

opr

-0.15

åĳ

-0.14

enko

-0.14

igid

-0.14

_ipc

-0.14

umen

-0.13

ofil

-0.13

ìĤ¬ëŀĳ

-0.13

POSITIVE LOGITS

 segment

0.35

 segments

0.32

 Segment

0.32

Segment

0.30

 show

0.29

segment

0.29

segments

0.28

Segments

0.26

 hosts

0.26

 studio

0.24

Activations Density 0.178%

information related to podcasts or radio shows

No Comments

No Known Activations