INDEX

Explanations

references to statistics and data within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

-animation

-0.15

_stdout

-0.15

ÎºÎ¿Ïį

-0.15

å«

-0.14

 narrator

-0.14

\Schema

-0.14

nh

-0.14

rete

-0.14

kup

-0.14

iego

-0.14

POSITIVE LOGITS

fan

0.22

 fandom

0.21

HQ

0.19

 cand

0.19

Fan

0.18

fan

0.18

 Merch

0.18

 candid

0.17

pap

0.17

 gallery

0.17

Activations Density 0.025%

references to statistics and data within a document

No Comments

No Known Activations