INDEX

Explanations

attributes in a code or configuration context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

Raf

-0.21

 ä¸ĥ

-0.19

 Seven

-0.19

 Rack

-0.18

 Eighth

-0.18

åħ«

-0.17

Riv

-0.17

 Seventh

-0.17

 Eight

-0.17

POSITIVE LOGITS

0.22

urer

0.16

ret

0.15

request

0.15

inine

0.15

ISA

0.15

ë¦Ħ

0.15

à¥¯

0.14

-request

0.14

Activations Density 0.031%

attributes in a code or configuration context

No Comments

No Known Activations