INDEX

Explanations

coordinating conjunctions that connect clauses or phrases

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

alla

-0.16

 Andreas

-0.15

ajan

-0.14

umn

-0.14

ble

-0.14

ikan

-0.14

esse

-0.14

adle

-0.14

 tick

-0.13

POSITIVE LOGITS

 deren

0.17

QUI

0.15

entai

0.15

leftright

0.14

éĿ

0.14

hores

0.14

Ã²a

0.14

atÃ¶r

0.14

 subsystem

0.14

 Retorna

0.13

Activations Density 0.400%

coordinating conjunctions that connect clauses or phrases

No Comments

No Known Activations