INDEX

Explanations

numerical identifiers or codes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ubb

-0.18

aus

-0.18

ey

-0.17

Ã¤tz

-0.16

Ð¼ÐµÑĩ

-0.16

gie

-0.15

ÑģÐ¾ÑĤ

-0.15

CLUDING

-0.14

tc

-0.14

ante

-0.14

POSITIVE LOGITS

ISA

0.16

0.15

çķª

0.15

à¸£à¸²à¸Ĭ

0.15

agma

0.15

pedia

0.15

/mock

0.14

otten

0.14

persistent

0.14

Activations Density 0.061%

numerical identifiers or codes

No Comments

No Known Activations