INDEX

Explanations

predicates and their variations in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

/Branch

-0.18

branches

-0.15

eri

-0.15

chod

-0.14

 Branch

-0.14

ording

-0.14

emin

-0.14

esel

-0.13

creature

-0.13

POSITIVE LOGITS

/manage

0.16

ÑģÑĮ

0.15

oca

0.15

erse

0.14

äº«

0.14

eel

0.14

saldo

0.14

/**↵↵

0.14

amo

0.14

å¤ªéĥİ

0.13

Activations Density 0.150%

predicates and their variations in sentences

No Comments

No Known Activations