INDEX

Explanations

numerical values related to measurements or statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onth

-0.15

 ValueEventListener

-0.15

edin

-0.14

erce

-0.13

REFIX

-0.13

/prom

-0.13

rov

-0.13

ide

-0.13

te

-0.13

ren

-0.13

POSITIVE LOGITS

ipeg

0.16

+↵

0.15

ï¼ĭ

0.14

silver

0.14

Ð°Ð»Ñİ

0.14

etc

0.14

ABCDEFGHIJKLMNOPQRSTUVWXYZ

0.14

à¤ķà¤°à¤£

0.14

Activations Density 0.002%

numerical values related to measurements or statistics

No Comments

No Known Activations